{"id":22894232,"url":"https://github.com/zib-iol/feddistill","last_synced_at":"2025-04-15T01:36:02.226Z","repository":{"id":223332472,"uuid":"759929605","full_name":"ZIB-IOL/FedDistill","owner":"ZIB-IOL","description":"Code to reproduce the experiments of the ICLR25 paper \"On the Byzantine-Resilience of Distillation-Based Federated Learning\" ","archived":false,"fork":false,"pushed_at":"2025-03-15T20:49:54.000Z","size":96,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T13:37:16.772Z","etag":null,"topics":["byzantine","deep-learning","federated-learning","knowledge-distillation","neural-networks","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2402.12265","language":"Python","has_issues":true,"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/ZIB-IOL.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":"citation.bib","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-19T15:56:16.000Z","updated_at":"2025-03-23T10:04:14.000Z","dependencies_parsed_at":"2024-02-19T18:33:49.342Z","dependency_job_id":"57e70c01-a65e-4ae9-a9c8-54d05b986228","html_url":"https://github.com/ZIB-IOL/FedDistill","commit_stats":null,"previous_names":["zib-iol/feddistill"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZIB-IOL%2FFedDistill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZIB-IOL%2FFedDistill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZIB-IOL%2FFedDistill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZIB-IOL%2FFedDistill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZIB-IOL","download_url":"https://codeload.github.com/ZIB-IOL/FedDistill/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248989872,"owners_count":21194660,"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":["byzantine","deep-learning","federated-learning","knowledge-distillation","neural-networks","pytorch"],"created_at":"2024-12-13T23:17:15.595Z","updated_at":"2025-04-15T01:36:02.219Z","avatar_url":"https://github.com/ZIB-IOL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## [ICLR25] On the Byzantine-Resilience of Distillation-Based Federated Learning\n\n*Authors: [Christophe Roux](http://christopheroux.de/), [Max Zimmer](https://maxzimmer.org/), [Sebastian Pokutta](http://www.pokutta.com/)*\n\nThis repository contains the code to reproduce the experiments from the ICLR25 paper [\"On the Byzantine-Resilience of Distillation-Based Federated Learning\"](https://arxiv.org/abs/2402.12265).\nThe code is based on [PyTorch 1.9](https://pytorch.org/) and the experiment-tracking platform [Weights \u0026 Biases](https://wandb.ai).\n\n### Structure and Usage\n#### Structure\nExperiments are started from the following file:\n\n- [`main.py`](main.py): Starts experiments using the dictionary format of Weights \u0026 Biases.\n\nThe rest of the project is structured as follows:\n\n- [`byzantine`](byzantine): Contains the attacks and defenses used in the paper.\n- [`runners`](runners): Contains classes to control the training and collection of metrics.\n- [`models`](models): Contains all model architectures used.\n- [`utilities.py`](utilities.py): Contains useful auxiliary functions and classes.\n- [`config.py`](config.py): Configuration for the datasets used in the experiments.\n- [`public_config.py`](public_config.py): Contains the configuration for the public datasets.\n- [`metrics.py`](metrics.py): Contains the metrics used in the experiments.\n- [`strategies.py`](strategies.py): Contains the different strategies used, such as FedAVG and FedDistill.\n\n\n#### Usage\nDefine the parameters in the [`main.py`](main.py) defaults-dictionary and run it with the --debug flag. Or, configure a sweep in Weights \u0026 Biases and run it from there (without the flag).\n\n### Citation\n\nIn case you find the paper or the implementation useful for your own research, please consider citing:\n\n```\n@inproceedings{roux2025on,\ntitle={On the Byzantine-Resilience of Distillation-Based Federated Learning},\nauthor={Christophe Roux and Max Zimmer and Sebastian Pokutta},\nbooktitle={The Thirteenth International Conference on Learning Representations},\nyear={2025},\nurl={https://openreview.net/forum?id=of6EuHT7de}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzib-iol%2Ffeddistill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzib-iol%2Ffeddistill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzib-iol%2Ffeddistill/lists"}