{"id":13408268,"url":"https://github.com/innovation-cat/Awesome-Federated-Machine-Learning","last_synced_at":"2025-03-14T12:32:29.846Z","repository":{"id":39613812,"uuid":"216189313","full_name":"innovation-cat/Awesome-Federated-Machine-Learning","owner":"innovation-cat","description":"Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond","archived":false,"fork":false,"pushed_at":"2024-04-12T04:21:14.000Z","size":421,"stargazers_count":1598,"open_issues_count":2,"forks_count":242,"subscribers_count":39,"default_branch":"master","last_synced_at":"2024-05-19T21:20:30.175Z","etag":null,"topics":["computer-vision","deep-learning","differential-privacy","distributed-computing","edge-computing","federated-learning","machine-learning","privacy-preserving-machine-learning","security"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/innovation-cat.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2019-10-19T10:35:34.000Z","updated_at":"2024-05-18T08:56:31.000Z","dependencies_parsed_at":"2023-02-14T17:46:09.756Z","dependency_job_id":"239d85d5-b5b8-47d5-8a2e-afd7d3a4f8d9","html_url":"https://github.com/innovation-cat/Awesome-Federated-Machine-Learning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/innovation-cat%2FAwesome-Federated-Machine-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/innovation-cat%2FAwesome-Federated-Machine-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/innovation-cat%2FAwesome-Federated-Machine-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/innovation-cat%2FAwesome-Federated-Machine-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/innovation-cat","download_url":"https://codeload.github.com/innovation-cat/Awesome-Federated-Machine-Learning/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243125540,"owners_count":20240276,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","differential-privacy","distributed-computing","edge-computing","federated-learning","machine-learning","privacy-preserving-machine-learning","security"],"created_at":"2024-07-30T20:00:51.779Z","updated_at":"2025-03-14T12:32:24.938Z","avatar_url":"https://github.com/innovation-cat.png","language":null,"funding_links":[],"categories":["Technical","Privacy-Preserving Federated Learning","Federated Learning","Federated Leaning","Uncategorized","acknowledgments","Privacy \u0026 Safety","Core Machine Learning Research"],"sub_categories":["awesome-*","Videos","DP auditing","Uncategorized","secret sharing","Federated and Privacy-Preserving ML"],"readme":"# Awesome Federated Machine Learning [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) \nFederated Learning (FL) is a new machine learning framework, which enables multiple devices collaboratively to train a shared model without compromising data privacy and security.  \n\n\u003cdiv align=center\u003e\n\u003cimg width=\"700\" src=\"images/cover.png\" alt=\"FL\"/\u003e\n\u003c/div\u003e\n\nThis repository aims to keep tracking the latest research advancements of federated learning, including but not limited to research papers, books, codes, tutorials, and videos.\n\n\n\n\n## Table of Contents\n\n - [Top Machine Learning Conferences](#top-machine-learning-conferences)\n     + [ICML](#icml)\u0026emsp;[ICLR](#iclr)\u0026emsp;[NeurIPS](#neurips)   \n - [Top Computer Vision Conferences](#top-computer-vision-conferences)\n     + [CVPR](#cvpr)\u0026emsp;[ICCV](#iccv)\u0026emsp;[ECCV](#eccv)   \n - [Top Artificial Intelligence and Data Mining Conferences](#top-artificial-intelligence-and-data-mining-conferences)\n     + [AAAI](#aaai)\u0026emsp;[AISTATS](#aistats)\u0026emsp;[KDD](#kdd) \t \n - [Books](#books)\n - [Papers (Research directions)](#papers)\n     + [Model Aggregation](#1-model-aggregation)\n\t + [Personalization](#2-personalization)\u0026emsp;\u0026emsp; \n\t + [Recommender system](#3-recommender-system)\n\t + [Security](#4-security)\u0026emsp;\u0026emsp;\n\t + [Survey](#5-survey)\u0026emsp;\u0026emsp;\n\t + [Efficiency](#7-efficiency)\u0026emsp;\u0026emsp;\n\t + [Optimization](#8-optimization)\u0026emsp;\u0026emsp; \n\t + [Fairness](#9-fairness)\u003cbr\u003e\n\t + [Application](#10-applications)\u0026emsp;\u0026emsp;\n\t + [Boosting](#11-boosting)\u0026emsp;\u0026emsp;\n\t + [Incentive mechanism](#12-incentive-mechanism)\n\t + [Unsupervised Learning](#13-unsupervised-learning)\u0026emsp;\u0026emsp;\n\t + [Heterogeneity](#14-heterogeneity)\u0026emsp;\u0026emsp;\n\t + [Client Selection](#15-client-selection)\n\t + [Graph Neural Networks](#16-graph-neural-networks)\n\t + [Other Machine Learning Paradigm](#18-other-machine-learning-paradigm)\n\t + [Computational Learning Theory](#19-computational-learning-theory)\n - [Google FL Workshops](#google-fl-workshops)\t \n - [Videos and Lectures](#videos-and-lectures)\n - [Tutorials and Blogs](#tutorials-and-blogs)\n - [Open-Sources](#open-sources)\n     + [Enterprise Grade](#enterprise-grade)\n\t + [Research Purpose](#research-purpose)\n\n\u0026nbsp; \n\n## Top Machine Learning Conferences\n\nIn this section, we will summarize Federated Learning papers accepted by top machine learning conference, Including NeurIPS, ICML, ICLR.\n\n### ICML \n\u003ctable border=0 cellpadding=0 cellspacing=0 \u003e\n    \u003ccol width=\"5%\" style='mso-width-source:userset;mso-width-alt:6848'\u003e\n\t\u003ccol width=\"65%\" style='mso-width-source:userset;mso-width-alt:26080'\u003e\n\t\u003ccol width=\"25%\" style='mso-width-source:userset;mso-width-alt:4032'\u003e\n\t\u003ccol width=\"5%\" style='mso-width-source:userset;mso-width-alt:4032'\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 width=\"5%\" align=\"center\"\u003eYears\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"65%\" align=\"center\"\u003eTitle\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"25%\" align=\"center\"\u003eAffiliations\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"5%\" align=\"center\"\u003eMaterials\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n        \u003ctd rowspan=50 height=950 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://icml.cc/Conferences/2023/Schedule?type=Poster\"\u003eICML 2023\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.10189.pdf\"\u003eA General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eAccenture Labs\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2306.00127.pdf\"\u003eSurrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eESAT-PSI, KU Leuven\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/JunyiZhu-AI/surrogate_model_extension\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://repository.tudelft.nl/islandora/object/uuid%3A44963ca4-46f8-49a1-9285-1c01e4d49402?collection=education\"\u003eLeadFL: Client Self-Defense against Model Poisoning in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eDelft University of Technology\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.05412.pdf\"\u003eAchieving Linear Speedup in Non-IID Federated Bilevel Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eMeta\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.03109.pdf\"\u003eOn the Convergence of Federated Averaging with Cyclic Client Participation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eCarnegie Mellon University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2304.13407.pdf\"\u003eFedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Hong Kong University of Science and Technology\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://guanh01.github.io/files/2023flash.pdf\"\u003eFlash: Concept Drift Adaptation in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Massachusetts\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://drive.google.com/drive/folders/1293G8IimzRus-WkjDacrqmEMzaHYSKMD\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.01068.pdf\"\u003ePersonalized Federated Learning under Mixture of Distributions\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of California, Los Angeles\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2307.13347.pdf\"\u003eFederated Heavy Hitter Recovery under Linear Sketching\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003eGoogle\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.04083.pdf\"\u003eImproving the Model Consistency of Decentralized Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eTsinghua University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.00771.pdf\"\u003eTowards Unbiased Training in Federated Open-world Semi-supervised Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Hong Kong Polytechnic University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2306.06508.pdf\"\u003eOptimizing the Collaboration Structure in Cross-Silo Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Illinois Urbana-Champaign\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/baowenxuan/FedCollab\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2205.13462.pdf\"\u003eFedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Chinese University of Hong Kong\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/lins-lab/fedbr\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/patel23a/patel23a.pdf\"\u003eFederated Online and Bandit Convex Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eToyota Technology Institute\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://aps.arxiv.org/pdf/2306.05275.pdf\"\u003eFederated Linear Contextual Bandits with User-level Differential Privacy\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Pennsylvania State University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/zhang23w/zhang23w.pdf\"\u003eFedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eShanghai Jiao Tong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/haozzh/FedCR\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2210.01785.pdf\"\u003eTabLeak: Tabular Data Leakage in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eETH Zurich\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2209.05578.pdf\"\u003eCocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eGeorgia Institute of Technology\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.10697.pdf\"\u003eThe Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eCarnegie Mellon University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.02219.pdf\"\u003eLESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eRensselaer Polytechnic Institute\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.06322.pdf\"\u003eOne-Shot Federated Conformal Prediction\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversite Paris-Saclay\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/pierreHmbt/FedCP-QQ\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/che23b/che23b.pdf\"\u003eFast Federated Machine Unlearning with Nonlinear Functional Theory\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eAuburn University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/che23b/che23b.pdf\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.02776.pdf\"\u003eEfficient Personalized Federated Learning via Sparse Model-Adaptation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eAlibaba\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/yxdyc/pFedGate\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.00543.pdf\"\u003eDoCoFL: Downlink Compression for Cross-Device Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eVMware Research\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/ullah23b/ullah23b.pdf\"\u003ePrivate Federated Learning with Autotuned Compression\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Johns Hopkins University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2211.14292.pdf\"\u003eAnalysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Linear Speedup and Partial Participation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eLinkedIn\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.10206.pdf\"\u003ePersonalized Subgraph Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eKAIST\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/JinheonBaek/FED-PUB\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2304.12961.pdf\"\u003eChameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eHong Kong University of Science and Technology \u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/ybdai7/Chameleon-durable-backdoor\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.11584.pdf\"\u003eDynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe University of Sydney\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/park23e/park23e.pdf\"\u003eTowards Understanding Ensemble Distillation in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eKAIST\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2306.07644.pdf\"\u003eSRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eOwkin Inc\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/owkin/SRATTA\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/wang23n/wang23n.pdf\"\u003eFedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eAlibaba\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/alibaba/FederatedScope/tree/master/benchmark/FedHPOBench\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.04969.pdf\"\u003eFederated Hypergradient Computation via Aggregated Iterative Differentiation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity at Buffalo\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"http://proceedings.mlr.press/v202/ye23b/ye23b.pdf\"\u003ePersonalized Federated Learning with Inferred Collaboration Graphs\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eShanghai Jiao Tong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/MediaBrain-SJTU/pFedGraph\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/pang23a/pang23a.pdf\"\u003eSecure Federated Correlation Test and Entropy Estimation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eCarnegie Mellon University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Qi-Pang/Federated-Correlation-Test\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2301.09223.pdf\"\u003eDoubly Adversarial Federated Bandits\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eLondon School of Economics and Political Science\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.19229.pdf\"\u003eFedDisco: Federated Learning with Discrepancy-Aware Collaboration\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eShanghai Jiao Tong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/MediaBrain-SJTU/FedDisco\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.10911.pdf\"\u003eRevisiting Weighted Aggregation in Federated Learning with Neural Networks\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eZhejiang University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2211.03942.pdf\"\u003ePrivacy-Aware Compression for Federated Learning Through Numerical Mechanism Design\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eMeta\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.05891.pdf\"\u003eAnchor Sampling for Federated Learning with Partial Client Participation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003ePurdue University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/HarliWu/FedAMD\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2208.03635.pdf\"\u003eFederated Adversarial Learning: A Framework with Convergence Analysis\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of British Columbia\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2209.15245.pdf\"\u003eFed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eDuke University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/chen23j/chen23j.pdf\"\u003eGuardHFL: Privacy Guardian for Heterogeneous Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Electronic Science and Technology of China\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2303.05786.pdf\"\u003eVertical Federated Graph Neural Network for Recommender System\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eNational University of Singapore\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/maiph123/VerticalGNN\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2210.14396.pdf\"\u003eFeDXL: Provable Federated Learning for Deep X-Risk Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eTexas A\u0026M University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Optimization-AI/ICML2023_FeDXL\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2306.05131.pdf\"\u003eConformal Prediction for Federated Uncertainty Quantification Under Label Shift\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eLagrange Mathematics and Computing Research Center\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2302.12559.pdf\"\u003eFrom Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniv. Lille, Inria\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"http://proceedings.mlr.press/v202/zhang23aa/zhang23aa.pdf\"\u003eNo One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eHarbin Institute of Technology\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Hypervoyager/PFL\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v202/guo23b/guo23b.pdf\"\u003eOut-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eJilin University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/YamingGuo98/FedIIR\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2305.17564.pdf\"\u003eFederated Conformal Predictors for Distributed Uncertainty Quantification\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eMIT\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/clu5/federated-conformal\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n        \u003ctd rowspan=37 height=703 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://icml.cc/Conferences/2022/Schedule?type=Poster\"\u003eICML 2022\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/liu22k/liu22k.pdf\"\u003eDeep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eShanghai Jiao Tong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Thinklab-SJTU/GAMF\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38984048/deep-neural-network-fusion-via-graph-matching-with-applications-to-model-ensemble-and-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2202.11453.pdf\"\u003eBitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eKAIST\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.cz/38984293/bitwidth-heterogeneous-federated-learning-with-progressive-weight-dequantization?ref=search-presentations-Bitwidth+Heterogeneous+Federated+Learning\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/18266.pdf\"\u003eslide\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.08829.pdf\"\u003eFedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Oulu\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/aelgabli/FedNew\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38983782/fednew-a-communicationefficient-and-privacypreserving-newtontype-method-for-federated-learning?ref=search-presentations-FedNew\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16854.pdf\"\u003eslide\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.02969.pdf\"\u003eFedNL: Making Newton-Type Methods Applicable to Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eKAUST\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://www.youtube.com/watch?v=_VYCEWT17R0\u0026ab_channel=FederatedLearningOneWorldSeminar\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17084.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38984020/fednl-making-newtontype-methods-applicable-to-federated-learning?ref=search-presentations-FedNL\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2203.04850.pdf\"\u003eFederated Minimax Optimization: Improved Convergence Analyses and Algorithms\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eCarnegie Mellon University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17436.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38984067/federated-minimax-optimization-improved-convergence-analyses-and-algorithms?ref=search-presentations-Federated+Minimax+Optimization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2205.02215.pdf\"\u003eFedNest: Federated Bilevel, Minimax, and Compositional Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Michigan\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/mc-nya/FedNest\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38983097/fednest-federated-bilevel-minimax-and-compositional-optimization?ref=search-presentations-FedNest%3A+Federated+Bilevel%2C+Minimax%2C+and+Compositional+Optimization\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17792_OrkxOe6.pdf\"\u003eslide\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2202.00580.pdf\"\u003eFishing for User Data in Large-Batch Federated Learning via Gradient Magnification\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Maryland\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/JonasGeiping/breaching\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16788.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.cz/38983313/fishing-for-user-data-in-largebatch-federated-learning-via-gradient-magnification?ref=search-presentations-Fishing+for+User+Data+in+Large-Batch+Federated+Learning+via+Gradient+Magnification\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.00187.pdf\"\u003eDisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Science and Technology of China\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/rong-dai/DisPFL\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983644/dispfl-towards-communicationefficient-personalized-federated-learning-via-decentralized-sparse-training?ref=recommended\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.10904.pdf\"\u003eFederated Learning with Positive and Unlabeled Data\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eXi’an Jiaotong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.ch/38984116/federated-learning-with-positive-and-unlabeled-data?ref=search-presentations-Federated+Learning+with+Positive+and+Unlabeled+Data\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.10341.pdf\"\u003eNeurotoxin: Durable Backdoors in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eSoutheast University;\u003cbr\u003ePrinceton University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/jhcknzzm/Federated-Learning-Backdoor/\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/18208.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38984143/neurotoxin-durable-backdoors-in-federated-learning?ref=search-presentations-Neurotoxin\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2111.00465.pdf\"\u003eDAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Cambridge\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16009.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983886/dadaquant-doublyadaptive-quantization-for-communicationefficient-federated-learning?ref=search-presentations-DAdaQuant\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2110.03681.pdf\"\u003eNeural Tangent Kernel Empowered Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eNC State University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/KAI-YUE/ntk-fed\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16732.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983411/neural-tangent-kernel-empowered-federated-learning?ref=search-presentations-Neural+Tangent+Kernel+Empowered+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://github.com/amitport/EDEN-Distributed-Mean-Estimation\"\u003eEDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eVMware Research\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/amitport/EDEN-Distributed-Mean-Estimation\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17680.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983975/eden-communicationefficient-and-robust-distributed-mean-estimation-for-federated-learning?ref=search-presentations-EDEN\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2202.07757.pdf\"\u003eArchitecture Agnostic Federated Learning for Neural Networks\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe University of Texas at Austin\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16926.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983435/architecture-agnostic-federated-learning-for-neural-networks?ref=search-presentations-Architecture+Agnostic+Federated+Learning+for+Neural+Networks\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/bao22b/bao22b.pdf\"\u003eFast Composite Optimization and Statistical Recovery in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eShanghai Jiao Tong University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17582.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983993/fast-composite-optimization-and-statistical-recovery-in-federated-learning?ref=search-presentations-Fast+Composite+Optimization+and+Statistical+Recovery+in+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2202.05318.pdf\"\u003ePersonalization Improves Privacy-Accuracy Tradeoffs in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eNew York University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16592.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983416/personalization-improves-privacyaccuracy-tradeoffs-in-federated-learning?ref=search-presentations-Personalization+Improves+Privacy%E2%80%93Accuracy+Tradeoffs+in+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2205.02719.pdf\"\u003eCommunication-Efficient Adaptive Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003ePennsylvania State University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/18274.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38983359/communicationefficient-adaptive-federated-learning?ref=search-presentations-Communication-Efficient+Adaptive+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.07977.pdf\"\u003ePersonalized Federated Learning via Variational Bayesian Inference\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eChinese Academy of Sciences\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/AllenBeau/pFedBayes\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38984249/personalized-federated-learning-via-variational-bayesian-inference?ref=search-presentations-Personalized+Federated+Learning+via+Variational+Bayesian\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/yi22a/yi22a.pdf\"\u003eQSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eNankai University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/LipingYi/QSFL\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/15968.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.ch/38984295/qsfl-a-twolevel-uplink-communication-optimization-framework-for-federated-learning?ref=search-presentations-QSFL\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.13673.pdf\"\u003eUnderstanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Minnesota\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38983965/understanding-clipping-for-federated-learning-convergence-and-clientlevel-differential-privacy?ref=search-presentations-Understanding+Clipping+for+Federated+Learning%3A+Convergence+and+Client-Level+Differential+Privacy\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/chen22s/chen22s.pdf\"\u003eThe Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eStanford University; \u003cbr\u003e Google Research\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17922_u8B84RF.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983067/the-poisson-binomial-mechanism-for-unbiased-federated-learning-with-secure-aggregation?ref=search-presentations-The+Poisson+Binomial+Mechanism\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/chen22c/chen22c.pdf\"\u003eThe Fundamental Price of Secure Aggregation in Differentially Private Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eStanford University; \u003cbr\u003e Google Research\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/google-research/federated/tree/master/private_linear_compression\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983654/the-fundamental-price-of-secure-aggregation-in-differentially-private-federated-learning?ref=search-presentations-The+Fundamental+Price+of+Secure+Aggregation+in+Differentially+Private+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.06818.pdf\"\u003eDisentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Science and Technology of China\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16881.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984212/disentangled-federated-learning-for-tackling-attributes-skew-via-invariant-aggregation-and-diversity-transferring?ref=search-presentations-Disentangled+Federated+Learning+for+TacklingAttributesSkewvia+Invariant+Aggregation+and+Diversity+Transferring\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.10185.pdf\"\u003eFederated Reinforcement Learning: Linear Speedup Under Markovian Sampling\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eGeogia Institute of Technology\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16656.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983157/federated-reinforcement-learning-linear-speedup-under-markovian-sampling?ref=search-presentations-Federated+Reinforcement+Learning%3A+Linear+Speedup+Under+Markovian+Sampling\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2205.11506.pdf\"\u003eOrchestra: Unsupervised Federated Learning via Globally Consistent Clustering\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Michigan\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/akhilmathurs/orchestra\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984080/orchestra-unsupervised-federated-learning-via-globally-consistent-clustering?ref=search-presentations-Orchestra%3A+Unsupervised+Federated+Learning+via+Globally+Consistent+Clustering\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/zhu22e/zhu22e.pdf\"\u003eResilient and Communication Efficient Learning for Heterogeneous Federated Systems\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eMichigan State University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16700.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983443/fedrescue-resilient-and-communication-efficient-learning-for-heterogeneous-federated-systems?ref=search-presentations-FedResCue\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/jin22e/jin22e.pdf\"\u003eAccelerated Federated Learning with Decoupled Adaptive Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eAuburn University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17540.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983363/accelerated-federated-learning-with-decoupled-adaptive-optimization?ref=search-presentations-Accelerated+Federated+Learning+with+Decoupled+Adaptive+Optimization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2102.06704.pdf\"\u003eProximal and Federated Random Reshuffling\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eKAUST\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/konstmish/rr_prox_fed\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984060/proximal-and-federated-random-reshuffling?ref=search-presentations-Proximal+and+Federated+Random+Reshuffling\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2111.09360.pdf\"\u003ePersonalized Federated Learning through Local Memorization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eInria\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/omarfoq/knn-per\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983601/personalized-federated-learning-through-local-memorization?ref=search-presentations-Personalized+Federated+Learning+through+Local+Memorization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/pillutla22a/pillutla22a.pdf\"\u003eFederated Learning with Partial Model Personalization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Washington\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/krishnap25/FL_partial_personalization\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16616.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983657/federated-learning-with-partial-model-personalization?ref=search-presentations-Federated+Learning+with+Partial+Model+Personalization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2110.05323.pdf\"\u003eProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eCISPA Helmholz Center for Information Security\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/a514514772/ProgFed\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984136/progfed-effective-communication-and-computation-efficient-federated-learning-by-progressive-training?ref=search-presentations-ProgFed%3A+Effective%2C+Communication%2C+and+Computation+Efficient+Federated+Learning+by+Progressive+Training\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://proceedings.mlr.press/v162/zhang22p/zhang22p.pdf\"\u003eFederated Learning with Label Distribution Skew via Logits Calibration\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eZhejiang University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16222_ACMSuAk.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983855/federated-learning-with-label-distribution-skew-via-logits-calibration?ref=search-presentations-Federated+Learning+with+Label+Distribution+Skew+via+Logits+Calibration\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2108.09875.pdf\"\u003eAnarchic Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eThe Ohio State University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/17061_kg1Vbwp.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983163/anarchic-federated-learning?ref=search-presentations-Anarchic+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.02465.pdf\"\u003eVirtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eHong Kong Baptist University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/wizard1203/VHL\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983852/virtual-homogeneity-learning-defending-against-data-heterogeneity-in-federated-learning?ref=search-presentations-Virtual+Homogeneity+Learning%3A+Defending+against+Data+Heterogeneity+in+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2206.02618.pdf\"\u003eGeneralized Federated Learning via Sharpness Aware Minimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of South Florida\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/16134.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38983752/generalized-federated-learning-via-sharpness-aware-minimization?ref=search-presentations-Generalized+Federated+Learning+via+Sharpness+Aware+Minimization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2105.11367.pdf\"\u003eFedScale: Benchmarking Model and System Performance of Federated Learning at Scale\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eUniversity of Michigan\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/SymbioticLab/FedScale\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984131/fedscale-benchmarking-model-and-system-performance-for-federated-learning-at-scale?ref=search-presentations-FedScale%3A+Benchmarking+Model+and+System+Performance+of+Federated+Learning+at+Scale\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2207.06936.pdf\"\u003eMulti-Level Branched Regularization for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003eSeoul National University\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"http://cvlab.snu.ac.kr/research/FedMLB/\"\u003eHomePage\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://icml.cc/media/icml-2022/Slides/18370.pdf\"\u003eslide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38984250/multilevel-branched-regularization-for-federated-learning?ref=search-presentations-Multi-Level+Branched+Regularization+for+Federated+Learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n        \u003ctd rowspan=18 height=342 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://icml.cc/Conferences/2021/Schedule?type=Poster\"\u003eICML 2021\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.06089.pdf\"\u003eGradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eHarvard University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38958558/gradient-disaggregation-breaking-privacy-in-federated-learning-by-reconstructing-the-user-participant-matrix\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://github.com/gdisag/gradient_disaggregation\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2105.05001.pdf\"\u003eFL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePeking University;\u003cbr\u003e Princeton University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959650/flntk-a-neural-tangent-kernelbased-framework-for-federated-learning-analysis\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2103.04628.pdf\"\u003ePersonalized Federated Learning using Hypernetworks\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eBar-Ilan University;\u003cbr\u003e NVIDIA \u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/AvivSham/pFedHN\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://avivsham.github.io/pfedhn/\"\u003eHomePage\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959583/personalized-federated-learning-using-hypernetworks\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2011.08474.pdf\"\u003eFederated Composite Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eStanford University;\u003cbr\u003e Google\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/hongliny/FCO-ICML21\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://www.youtube.com/watch?v=tKDbc60XJks\u0026ab_channel=FederatedLearningOneWorldSeminar\"\u003evideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://hongliny.github.io/files/FCO_ICML21/FCO_ICML21_slides.pdf\"\u003eslides\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2102.07078.pdf\"\u003eExploiting Shared Representations for Personalized Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Texas at Austin;\u003cbr\u003e University of Pennsylvania\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/lgcollins/FedRep\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959519/exploiting-shared-representations-for-personalized-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2105.10056.pdf\"\u003eData-Free Knowledge Distillation for Heterogeneous Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMichigan State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/zhuangdizhu/FedGen\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959429/datafree-knowledge-distillation-for-heterogeneous-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2003.03196.pdf\"\u003eFederated Continual Learning with Weighted Inter-client Transfer\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAIST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/wyjeong/FedWeIT\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959323/federated-continual-learning-with-weighted-interclient-transfer\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2102.04635.pdf\"\u003eFederated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of Iowa\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959235/federated-deep-auc-maximization-for-hetergeneous-data-with-a-constant-communication-complexity\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2102.03198.pdf\"\u003eBias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of Tokyo\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959169/biasvariance-reduced-local-sgd-for-less-heterogeneous-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2104.08776.pdf\"\u003eFederated Learning of User Verification Models Without Sharing Embeddings\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eQualcomm\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38958858/federated-learning-of-user-verification-models-without-sharing-embeddings\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2105.05883.pdf\"\u003eClustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eAccenture\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Accenture//Labs-Federated-Learning/tree/clustered_sampling\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959618/clustered-sampling-lowvariance-and-improved-representativity-for-clients-selection-in-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2012.04221.pdf\"\u003eDitto: Fair and Robust Federated Learning Through Personalization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCMU;\u003cbr\u003e Facebook AI\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/litian96/ditto\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38955195/ditto-fair-and-robust-federated-learning-through-personalization\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2103.00697.pdf\"\u003eHeterogeneity for the Win: One-Shot Federated Clustering\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCMU\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959380/heterogeneity-for-the-win-oneshot-federated-clustering\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2102.06387.pdf\"\u003eThe Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959306/the-distributed-discrete-gaussian-mechanism-for-federated-learning-with-secure-aggregation\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n        \u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"http://proceedings.mlr.press/v139/acar21a/acar21a.pdf\"\u003eDebiasing Model Updates for Improving Personalized Federated Training\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eBoston University;\u003cbr\u003e Arm \u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959212/debiasing-model-updates-for-improving-personalized-federated-training\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2103.03228.pdf\"\u003eOne for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eToyota;\u003cbr\u003eBerkeley;\u003cbr\u003e Cornell University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/rlphilli/Collaborative-Incentives\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959135/one-for-one-or-all-for-all-equilibria-and-optimality-of-collaboration-in-federated-learning\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n        \u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.08283.pdf\"\u003eCRFL: Certifiably Robust Federated Learning against Backdoor Attacks\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUIUC;\u003cbr\u003eIBM\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/AI-secure/CRFL\"\u003ecode\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38959047/crfl-certifiably-robust-federated-learning-against-backdoor-attacks\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n        \u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://assets.amazon.science/11/23/3e0cfaf1456d80ecf3f37a2cd812/federated-learning-under-arbitrary-communication-patterns.pdf\"\u003eFederated Learning under Arbitrary Communication Patterns\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eIndiana University;\u003cbr\u003e Amazon\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38959048/federated-learning-under-arbitrary-communication-patterns\"\u003evideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n        \u003ctd rowspan=6 height=114 class=xl6519452 style='height:85.5pt' align=\"center\"\u003e\u003ca href=\"https://icml.cc/Conferences/2020/Schedule?type=Poster\"\u003eICML 2020\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6619452 width=815 style='width:611pt' align=\"center\"\u003e\u003ca href=\"http://proceedings.mlr.press/v119/hamer20a/hamer20a.pdf\"\u003eFedBoost: A Communication-Efficient Algorithm for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38928463/fedboost-a-communicationefficient-algorithm-for-federated-learning?ref=speaker-16993-latest\"\u003eVideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2007.07682.pdf\"\u003eFetchSGD: Communication-Efficient Federated Learning with Sketching\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUC Berkeley;\u003cbr\u003eJohns Hopkins University;\u003cbr\u003eAmazon\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38928454/fetchsgd-communicationefficient-federated-learning-with-sketching\"\u003eVideo\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://github.com/kiddyboots216/CommEfficient\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/1910.06378.pdf\"\u003eSCAFFOLD: Stochastic Controlled Averaging for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eEPFL;\u003cbr\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38927610/scaffold-stochastic-controlled-averaging-for-federated-learning\"\u003eVideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2004.10342\"\u003eFederated Learning with\n\t\tOnly Positive Labels\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://slideslive.com/38928322/federated-learning-with-only-positive-labels\"\u003eVideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2004.01442.pdf\"\u003eFrom Local SGD to Local Fixed-Point Methods for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMoscow Institute of Physics and Technology;\u003cbr\u003eKAUST\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/Slides/icml/2020/virtual(no-parent)-15-18-00UTC-6590-from_local_sgd.pdf\"\u003eSlide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38928320/from-local-sgd-to-local-fixed-point-methods-for-federated-learning\"\u003eVideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6619452 width=815 style='height:14.25pt;width:611pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/2002.11364\"\u003eAcceleration for Compressed Gradient Descent in Distributed and Federated Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAUST\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://icml.cc/media/Slides/icml/2020/virtual(no-parent)-15-19-00UTC-6191-acceleration_fo.pdf\"\u003eSlide\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://slideslive.com/38927921/acceleration-for-compressed-gradient-descent-in-distributed-optimization\"\u003eVideo\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n        \u003ctd rowspan=3 height=57 class=xl6519452 style='height:85.5pt' align=\"center\"\u003e\u003ca href=\"https://icml.cc/Conferences/2019/Schedule?type=Poster\"\u003eICML 2019\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6619452 width=815 style='width:611pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/1905.12022.pdf\"\u003eBayesian Nonparametric Federated Learning of Neural Networks\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eIBM\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/IBM/probabilistic-federated-neural-matching\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6619452 width=815 style='height:14.25pt;width:611pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/abs/1811.12470\"\u003eAnalyzing Federated Learning through an Adversarial Lens\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePrinceton University;\u003cbr\u003eIBM\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/inspire-group/ModelPoisoning\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6619452 width=815 style='height:14.25pt;width:611pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/1902.00146.pdf\"\u003eAgnostic Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGoogle \u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\u003c/table\u003e\n\n\n### ICLR\n\n\u003ctable border=0 cellpadding=0 cellspacing=0 \u003e\n    \u003ccol width=\"5%\" style='mso-width-source:userset;mso-width-alt:6848'\u003e\n\t\u003ccol width=\"65%\" style='mso-width-source:userset;mso-width-alt:26080'\u003e\n\t\u003ccol width=\"25%\" style='mso-width-source:userset;mso-width-alt:4032'\u003e\n\t\u003ccol width=\"5%\" style='mso-width-source:userset;mso-width-alt:4032'\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 width=\"5%\" align=\"center\"\u003eYears\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"65%\" align=\"center\"\u003eTitle\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"25%\" align=\"center\"\u003eAffiliation\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 width=\"5%\" align=\"center\"\u003eMaterials\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n\t\t\u003ctd rowspan=47 height=893 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/group?id=ICLR.cc/2023/Conference\"\u003eICLR 2023\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=2QGJXyMNoPz\"\u003eMocoSFL: enabling cross-client collaborative self-supervised learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eArizona State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/SonyAI/MocoSFL\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=SXZr8aDKia\"\u003ePersonalized Federated Learning with Feature Alignment and Classifier Collaboration \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eTsinghua University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=3RhuF8foyPW\"\u003eSingle-shot General Hyper-parameter Optimization for Federated Learning \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eIBM Research\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Mpa3tRJFBb\"\u003eWhere to Begin? On the Impact of Pre-Training and Initialization in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMeta AI\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=IPrzNbddXV\"\u003eFedExP: Speeding Up Federated Averaging via Extrapolation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCarnegie Mellon University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Divyansh03/FedExP\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=mMNimwRb7Gr\"\u003eTurning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMichigan State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/illidanlab/FOSTER\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=VA1YpcNr7ul\"\u003eDASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAUST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/mysteryresearcher/dasha\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=38m4h8HcNRL\"\u003eFederated Neural Bandits\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eNational University of Singapore\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/daizhongxiang/Federated-Neural-Bandits\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=VzwfoFyYDga\"\u003eMachine Unlearning of Federated Clusters\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Illinois Urbana-Champaign\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/thupchnsky/mufc\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=U9yFP90jU0\"\u003eFedFA: Federated Feature Augmentation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eETH Zurich\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/tfzhou/FedFA\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=dZrQR7OR11\"\u003eFederated Learning as Variational Inference: A Scalable Expectation Propagation Approach\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCarnegie Mellon University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/HanGuo97/expectation-propagation\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=cRxYWKiTan\"\u003eBetter Generative Replay for Continual Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Virginia\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/daiqing98/FedCIL\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=hDDV1lsRV8\"\u003eFederated Learning from Small Datasets\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity Hospital Essen\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/kampmichael/FedDC\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=R1U5G2spbLd\"\u003eFederated Nearest Neighbor Machine Translation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Science and Technology of China\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/duyichao/FedNN-MT\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=3aBuJEza5sq\"\u003eTest-Time Robust Personalization for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eWestlake University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/LINs-lab/FedTHE\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=pf8RIZTMU58\"\u003eDepthFL : Depthwise Federated Learning for Heterogeneous Clients\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eSeoul National University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=rzrqh85f4Sc\"\u003eTowards Addressing Label Skews in One-Shot Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eNational University of Singapore\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Xtra-Computing/FedOV\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=EXnIyMVTL8s\"\u003eTowards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eNational University of Singapore\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/bytedance/FedDecorr\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=V7CYzdruWdm\"\u003eBias Propagation in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eNational University of Singapore\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/privacytrustlab/bias_in_FL\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=A9WQaxYsfx\"\u003ePanning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Maryland\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=jh1nCir1R3d\"\u003eSWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Maryland\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/umd-huang-lab/SWIFT\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=TVY6GoURrw\"\u003ePrivate Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Southern California\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=QsCSLPP55Ku\"\u003eEffective passive membership inference attacks in federated learning against overparameterized models\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePurdue University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=bZjxxYURKT\"\u003eFedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of Sydney\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=9aokcgBVIj1\"\u003eFiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Cambridge\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/cambridge-mlg/fit\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Hnk1WRMAYqg\"\u003eMultimodal Federated Learning via Contrastive Representation Ensemble\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eTsinghua University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=ElC6LYO4MfD\"\u003eFaster federated optimization under second-order similarity\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePrinceton University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=oJpVVGXu9i\"\u003eShare Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eETH Zurich\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/shenzebang/CENTAUR-Privacy-Federated-Representation-Learning\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=29V3AWjVAFi\"\u003eThe Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of Texas at Austin\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=hxEIgUXLFF\"\u003ePerFedMask: Personalized Federated Learning with Optimized Masking Vectors\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of British Columbia\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/MehdiSet/PerFedMask\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=6P9Y25Pljl6\"\u003eFedDAR: Federated Domain-Aware Representation Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eHarvard University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/zlz0414/FedDAR\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=ytZIYmztET\"\u003eEPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGeorge Mason University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/MingruiLiu-ML-Lab/episode\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Xo2E217_M4n\"\u003eFLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePurdue University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/KaiyuanZh/FLIP\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=-EHqoysUYLx\"\u003eGeneralization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eRenmin University of China\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=eKllxpLOOm\"\u003eCombating Exacerbated Heterogeneity for Robust Models in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eHong Kong Baptist University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/ZFancy/SFAT\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=uhLAcrAZ9cJ\"\u003eEfficient Federated Domain Translation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePurdue University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=fWWFv--P0xP\"\u003eOn the Importance and Applicability of Pre-Training for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe Ohio State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/andytu28/FPS_Pre-training\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=FUiDMCr_W4o\"\u003eA Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of California, Los Angeles\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=FIrQfNSOoTr\"\u003eInstance-wise Batch Label Restoration via Gradients in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eBeihang University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/BUAA-CST/iLRG\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=r0BrY4BiEXO\"\u003eDecepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Maryland\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=TDf-XFAwc79\"\u003eMeta Knowledge Condensation for Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCenter for Frontier AI Research\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=_hb4vM3jspB\"\u003eData-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eWilliam \u0026 Mary\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Kf7Yyf4O0u\"\u003eCANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Warwick\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/facebookresearch/canife\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=k1FHgri5y3-\"\u003eSparse Random Networks for Communication-Efficient Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eStanford University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/BerivanIsik/sparse-random-networks\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=nAgdXgfmqj\"\u003eHyperparameter Optimization through Neural Network Partitioning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Cambridge\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=2L9gzS80tA4\"\u003eDoes Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMIT CSAIL\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=2L9gzS80tA4\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=pfuqQQCB34\"\u003eVariance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAUST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n\t\t\u003ctd rowspan=21 height=399 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/group?id=ICLR.cc/2022/Conference\"\u003eICLR 2022\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2111.04706.pdf\"\u003eBayesian Framework for Gradient Leakage\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eETH Zurich\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/eth-sri/bayes-framework-leakage\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=WHA8009laxu\"\u003eFederated Learning from only unlabeled data with class-conditional-sharing clients\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe University of Tokyo;\u003cbr\u003eThe Chinese University of Hong Kong\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/lunanbit/FedUL\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2108.06869.pdf\"\u003eFedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCarnegie Mellon University;\u003cbr\u003eUniversity of Illinois at Urbana-Champaign;\u003cbr\u003eUniversity of Washington\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=541PxiEKN3F\"\u003eAcceleration of Federated Learning with Alleviated Forgetting in Local Training\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eTsinghua University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/Zoesgithub/FedReg\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2108.06098.pdf\"\u003eFedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePOSTECH\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/South-hw/FedPara_ICLR22\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Xo0lbDt975\"\u003eAn Agnostic Approach to Federated Learning with Class Imbalance\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Pennsylvania \u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/shenzebang/Federated-Learning-Pytorch\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=_QLmakITKg\"\u003eEfficient Split-Mix Federated Learning for On-Demand and In-Situ Customization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eMichigan State University;\u003cbr\u003eThe University of Texas at Austin\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/illidanlab/SplitMix\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=fwzUgo0FM9v\"\u003eRobbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Maryland;\u003cbr\u003eNew York University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/lhfowl/robbing_the_fed\"\u003ecode (Minimum)\u003c/a\u003e\u003cbr\u003e\u003ca href=\"https://github.com/JonasGeiping/breaching\"\u003ecode (Comprehensive)\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=2sDQwC_hmnM\"\u003eZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Cambridge;\u003cbr\u003eUniversity of Oxford\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=nwKXyFvaUm\"\u003eDiverse Client Selection for Federated Learning via Submodular Maximization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eIntel;\u003cbr\u003eCarnegie Mellon University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/melodi-lab/divfl\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2202.00280.pdf\"\u003eRecycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank? \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePurdue University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/shams-sam/FedOptim\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=E4EE_ohFGz\"\u003eDiurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Maryland;\u003cbr\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/google-research/federated/tree/7525c36324cb022bc05c3fce88ef01147cae9740/periodic_distribution_shift\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2110.15210.pdf\"\u003eTowards Model Agnostic Federated Learning Using Knowledge Distillation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eEPFL\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=oVE1z8NlNe\"\u003eDivergence-aware Federated Self-Supervised Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003e Nanyang Technological University;\u003cbr\u003eSenseTime\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2110.14216.pdf\"\u003eWhat Do We Mean by Generalization in Federated Learning? \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eStanford University;\u003cbr\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/google-research/federated/tree/master/generalization\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2106.06042.pdf\"\u003eFedBABU: Toward Enhanced Representation for Federated Image Classification \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAIST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/jhoon-oh/FedBABU\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2006.09365.pdf\"\u003eByzantine-Robust Learning on Heterogeneous Datasets via Bucketing \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eEPFL\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/liehe/byzantine-robust-noniid-optimizer\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2201.12467.pdf\"\u003eImproving Federated Learning Face Recognition via Privacy-Agnostic Clusters\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eAibee\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/IrvingMeng/MagFace\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=H0oaWl6THa\"\u003eHybrid Local SGD for Federated Learning with Heterogeneous Communications \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eUniversity of Texas;\u003cbr\u003e\tPennsylvania State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2107.00778.pdf\"\u003eOn Bridging Generic and Personalized Federated Learning for Image Classification \u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe Ohio State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/hongyouc/Fed-RoD\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2110.10342.pdf\"\u003eMinibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAIST;\u003cbr\u003eMIT\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.15pt'\u003e\n\t\t\u003ctd rowspan=10 height=190 class=xl6519452 style='height:242.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/group?id=ICLR.cc/2021/Conference\"\u003eICLR 2021\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=B7v4QMR6Z9w\"\u003eFederated Learning Based on Dynamic Regularization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eBoston University;\u003cbr\u003eARM\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=jDdzh5ul-d\"\u003eAchieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe Ohio State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2010.01264.pdf\"\u003eHeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eDuke University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/dem123456789/HeteroFL-Computation-and-Communication-Efficient-Federated-Learning-for-Heterogeneous-Clients\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=Ogga20D2HO-\"\u003eFedMix: Approximation of Mixup under Mean Augmented Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAIST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2010.05273.pdf\"\u003eFederated Learning via Posterior Averaging: A New Perspective and Practical Algorithms\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCMU; Google\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/alshedivat/fedpa\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2003.00295.pdf\"\u003eAdaptive Federated Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eGoogle\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/google-research/federated/tree/master/optimization\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=ehJqJQk9cw\"\u003ePersonalized Federated Learning with First Order Model Optimization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eStanford University; NVIDIA\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=6YEQUn0QICG\"\u003eFedBN: Federated Learning on Non-IID Features via Local Batch Normalization\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003ePrinceton University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/med-air/FedBN\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2009.01974.pdf\"\u003eFedBE: Making Bayesian Model Ensemble Applicable to Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eThe Ohio State University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=ce6CFXBh30h\"\u003eFederated Semi-Supervised Learning with Inter-Client Consistency \u0026 Disjoint Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eKAIST\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/wyjeong/FedMatch\"\u003ecode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt'\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd rowspan=7 height=133 class=xl6519452 style='height:85.5pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/group?id=ICLR.cc/2020/Conference\"\u003eICLR 2020\u003c/a\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6619452 width=815 style='width:611pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=HJezF3VYPB\"\u003eFederated Adversarial Domain Adaptation\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eBoston University;\u003cbr\u003eColumbia University;\u003cbr\u003eRutgers University\u003c/font\u003e\u003c/td\u003e\n\t\t\u003ctd class=xl6519452 align=\"center\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=rkgyS0VFvr\"\u003eDBA: Distributed Backdoor Attacks against Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eZhejiang University;\u003cbr\u003eIBM Research\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca href=\"https://github.com/AI-secure/DBA\"\u003eCode\u003c/a\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n    \u003ctr height=19 style='height:14.25pt'\u003e\n\t\t\u003ctd height=19 class=xl6519452 style='height:14.25pt' align=\"center\"\u003e\u003ca href=\"https://openreview.net/pdf?id=ByexElSYDr\"\u003eFair Resource Allocation in Federated Learning\u003c/a\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003cfont size=\"2\"\u003eCMU;\u003cbr\u003eFacebook AI\u003c/font\u003e\u003c/td\u003e\n        \u003ctd class=xl6519452 align=\"center\"\u003e\u003ca ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finnovation-cat%2FAwesome-Federated-Machine-Learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finnovation-cat%2FAwesome-Federated-Machine-Learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finnovation-cat%2FAwesome-Federated-Machine-Learning/lists"}