Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/beiyuouo/awesome-asynchronous-federated-learning

📦 Collect some Asynchronous Federated Learning papers.
https://github.com/beiyuouo/awesome-asynchronous-federated-learning

List: awesome-asynchronous-federated-learning

asynchronous awesome distributed-computing federated-learning machine-learning paper paper-list papers

Last synced: about 2 months ago
JSON representation

📦 Collect some Asynchronous Federated Learning papers.

Host: GitHub
URL: https://github.com/beiyuouo/awesome-asynchronous-federated-learning
Owner: beiyuouo
License: mit
Created: 2021-09-25T08:21:37.000Z (almost 3 years ago)
Default Branch: main
Last Pushed: 2024-01-11T04:45:53.000Z (6 months ago)
Last Synced: 2024-05-11T05:53:28.260Z (2 months ago)
Topics: asynchronous, awesome, distributed-computing, federated-learning, machine-learning, paper, paper-list, papers
Language: Python
Homepage: https://www.bj-yan.top/awesome-asynchronous-federated-learning
Size: 101 KB
Stars: 76
Watchers: 2
Forks: 6
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Lists

ultimate-awesome - awesome-asynchronous-federated-learning - 📦 Collect some Asynchronous Federated Learning papers. (Other Lists / Julia Lists)

README

        # Awesome Asynchronous Federated Learning

[[GitHub]](https://github.com/beiyuouo/awesome-asynchronous-federated-learning) [[Web]](https://www.bj-yan.top/awesome-asynchronous-federated-learning)

Collect some **Asynchronous Federated Learning** papers.

Please give me a **⭐star** if you find it useful (❁´◡`❁).

If you find some overlooked papers, please open issues or pull requests(recommended), following the `Contributing` section.

**Last Update: Jan 11, 2024 12:45:53**

## Fully Asynchronous

### 2022

- **[AsyncFedED]** AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation (_arXiv_) [[PDF]](https://arxiv.org/abs/2205.13797)

### 2021

- **[FedSA]** FedSA: A staleness-aware asynchronous Federated Learning algorithm with non-IID data (_FGCS Elsevier_) [[PDF]](https://www.sciencedirect.com/science/article/abs/pii/S0167739X21000649)

- **[FedDR]** FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization (_ResearchGate_) [[PDF]](https://www.researchgate.net/publication/349880146_FedDR_--_Randomized_Douglas-Rachford_Splitting_Algorithms_for_Nonconvex_Federated_Composite_Optimization?enrichId=rgreq-75be60e8182e96c4544e855110f94039-XXX&enrichSource=Y292ZXJQYWdlOzM0OTg4MDE0NjtBUzoxMDI2MDIwMjYyMDE5MDc4QDE2MjE2MzM3MDE0ODA%3D&el=1_x_2&_esc=publicationCoverPdf)

- An Asynchronous Federated Learning Approach for a Security Source Code Scanner (_ICISSP_) [[PDF]](https://www.researchgate.net/publication/349402236_An_Asynchronous_Federated_Learning_Approach_for_a_Security_Source_Code_Scanner?enrichId=rgreq-91295cf9d6b78d8ff49812fae57abbf2-XXX&enrichSource=Y292ZXJQYWdlOzM0OTQwMjIzNjtBUzoxMDA2NjY1OTE4ODQwODM1QDE2MTcwMTkyNjY2MDQ%3D&el=1_x_2&_esc=publicationCoverPdf)

- **[FedConD]** Asynchronous Federated Learning for Sensor Data with Concept Drift (_arXiv_) [[PDF]](https://arxiv.org/abs/2109.00151)

### 2020

- Adaptive Task Allocation for Asynchronous Federated and Parallelized Mobile Edge Learning (_arXiv_) [[PDF]](https://arxiv.org/abs/1905.01656)

- **[ASO-Fed]** Asynchronous Online Federated Learning for Edge Devices with Non-IID Data (_Big Data_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9378161/)

### 2019

- **[FedAsync]** Asynchronous Federated Optimization (_OPT_) [[PDF]](https://arxiv.org/abs/1903.03934) [[Code]](https://github.com/xcgoner/async_fl)

- **[DP-AFL]** Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics (_TII_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/8843942)

- **[TWAFL]** Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation (_TNNLS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/8945292)

### 2018

- Federated learning for ultra-reliable low-latency V2V communications (_GLOBECOM_) [[PDF]](https://arxiv.org/abs/1807.08127)

## K-Asynchronous or Semi-Asynchronous

### 2022

- **[KAFL]** KAFL: Achieving High Training Efficiency for Fast-K Asynchronous Federated Learning (_ICDCS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9912266)

- **[WKAFL]** Towards Efficient and Stable K-Asynchronous Federated Learning With Unbounded Stale Gradients on Non-IID Data (_IEEE TPDS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9712243)

- **[FedBuff]** Federated Learning with Buffered Asynchronous Aggregation (_AISTATS_) [[PDF]](https://arxiv.org/abs/2106.06639)

### 2021

- **[FedSA]** FedSA: A Semi-Asynchronous Federated Learning Mechanism in Heterogeneous Edge Computing (_IEEE JSAC_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9562538)

- **[SAFA]** SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead (_IEEE Transactions on Computers_) [[PDF]](https://www.computer.org/csdl/journal/tc/2021/05/09093123/1jNu0qlnwSk)

## Privacy-Preserving

### 2021

- **[AFSGD-VP]** Privacy-Preserving Asynchronous Vertical Federated Learning Algorithms for Multiparty Collaborative Learning (_TNNLS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9463409)

- **[BASecAgg]** Secure Aggregation for Buffered Asynchronous Federated Learning (_arXiv_) [[PDF]](https://arxiv.org/abs/2110.02177)

## Hierarchical or Tier-based

### 2023

- **[TimelyFL]** TimelyFL: Heterogeneity-Aware Asynchronous Federated Learning With Adaptive Partial Training (_CVPR_) [[PDF]](https://openaccess.thecvf.com/content/CVPR2023W/FedVision/html/Zhang_TimelyFL_Heterogeneity-Aware_Asynchronous_Federated_Learning_With_Adaptive_Partial_Training_CVPRW_2023_paper.html)

- **[AHFL]** Timely Asynchronous Hierarchical Federated Learning: Age of Convergence (_arXiv_) [[PDF]](https://arxiv.org/abs/2306.12400)

- **[HiFlash]** HiFlash: Communication-Efficient Hierarchical Federated Learning With Adaptive Staleness Control and Heterogeneity-Aware Client-Edge Association (_T-PDS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/10021868)

- Scheduling and Aggregation Design for Asynchronous Federated Learning Over Wireless Networks (_IEEE JSAC_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/10041216)

### 2022

- Client-Edge-Cloud Hierarchical Federated Learning (_IEEE/ACM SEC_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9996746)

- Hierarchical Federated Learning With Quantization: Convergence Analysis and System Design (_IEEE TWC_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9834296)

### 2021

- Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients (_arXiv_) [[PDF]](https://arxiv.org/abs/2102.06329)

- Time Minimization in Hierarchical Federated Learning (_arXiv_) [[PDF]](https://arxiv.org/abs/2106.06639)

- **[FedAT]** FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers (_arXiv_) [[PDF]](https://arxiv.org/abs/2010.05958\)

### 2020

- **[TiFL]** TiFL: A Tier-based Federated Learning System (_HPDC_) [[PDF]](https://dl.acm.org/doi/abs/10.1145/3369583.3392686)

## Model Heterogeneous

### 2023

- **[MA-FL]** Asynchronous Multi-Model Federated Learning over Wireless Networks: Theory, Modeling, and Optimization (_arXiv_) [[PDF]](https://arxiv.org/abs/2305.13503)

## Fairness

### 2022

- Client Selection for Asynchronous Federated Learning with Fairness Consideration (_ICC Workshop_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9814669)

- Online Client Selection for Asynchronous Federated Learning With Fairness Consideration (_IEEE TWC_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9916164)

## Asynchronous Federated Increment Learning

### 2023

- **[AFCL]** Asynchronous Federated Continual Learning (_CVPR FedVision Workshop_) [[PDF]](https://arxiv.org/abs/2304.03626) [[Code]](https://github.com/LTTM/FedSpace)

## Vertical Asynchronous Federated Learning

### 2021

- **[AFSGD-VP]** Privacy-Preserving Asynchronous Vertical Federated Learning Algorithms for Multiparty Collaborative Learning (_TNNLS_) [[PDF]](https://ieeexplore.ieee.org/abstract/document/9463409)

### 2020

- **[VAFL]** VAFL: a Method of Vertical Asynchronous Federated Learning (_ICML 2020_) [[PDF]](https://arxiv.org/abs/2109.04269)

## Application

### 2018

- Asynchronous Federated Learning for Geospatial Applications (_ECML PKDD_) [[PDF]](https://link.springer.com/chapter/10.1007/978-3-030-14880-5_2)

## General Federated Learning

- **[FedAvg]** Communication-Efficient Learning of Deep Networks from Decentralized Data (_AISTATS_) [[PDF]](https://arxiv.org/abs/1602.05629.pdf)

## Benchmarks

- **[LEAF]** Leaf: A benchmark for federated settings (_arXiv_) [[PDF]](https://arxiv.org/abs/1812.01097) [[GitHub]](https://github.com/TalwalkarLab/leaf/)

## Libraries(Which support Asynchronous Federated Learning)

- **[FedML]** FedML: A Research Library and Benchmark for Federated Machine Learning (_arXiv_) [[Home]](https://fedml.ai/) [[PDF]](https://arxiv.org/abs/2007.13518) [[GitHub]](https://github.com/FedML-AI/FedML) [[Docs]](https://doc.fedml.ai/)

- **[FedHF]** FedHF: 🔨 A Flexible Federated Learning Simulator.  [[GitHub]](https://github.com/beiyuouo/fedhf)

- **[FederatedScope]** FederatedScope: A Flexible Federated Learning Platform for Heterogeneity  [[Home]](https://www.federatedscope.io/) [[GitHub]](https://github.com/alibaba/FederatedScope) [[PDF]](https://arxiv.org/pdf/2204.05011.pdf)

- **[PySyft]** PySyft: A Library for Easy Federated Learning (_Studies in Computational Intelligence_) [[GitHub]](https://github.com/OpenMined/PySyft) [[PDF]](https://link.springer.com/chapter/10.1007/978-3-030-70604-3_5)

- **[FedLab]** FedLab: A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research.  [[GitHub]](https://github.com/SMILELab-FL/FedLab) [[Docs]](https://fedlab.readthedocs.io/)

## Survey

- **[Open Problem]** Advances and Open Problems in Federated Learning (_FnTML_) [[PDF]](https://arxiv.org/abs/1912.04977)

- Asynchronous Federated Learning on Heterogeneous Devices: A Survey (_arXiv_) [[PDF]](https://arxiv.org/abs/2109.04269)

## Theory

- On the Convergence of FedAvg on Non-IID Data (_ICLR 2020_) [[PDF]](https://arxiv.org/abs/1907.02189) [[GitHub]](https://github.com/lx10077/fedavgpy)

## Heterogeneous

- **[FedProx]** Federated Optimization in Heterogeneous Networks (_MLSys 2020_) [[PDF]](https://arxiv.org/abs/1812.06127) [[GitHub]](https://github.com/litian96/FedProx)

- **[FedBN]** FedBN: Federated Learning on Non-IID Features via Local Batch Normalization (_ICLR 2021_) [[PDF]](https://openreview.net/pdf?id=6YEQUn0QICG) [[GitHub]](https://github.com/med-air/FedBN)

- **[Pisces]** Pisces: Efficient Federated Learning via Guided Asynchronous Training (_ACM SoCC 2022_) [[PDF]](https://dl.acm.org/doi/abs/10.1145/3542929.3563463) [[GitHub]](https://github.com/SamuelGong/Pisces)

## Client Selection

[WIP]

## Ungrouped Papers

[WIP]

## Blog

[WIP]

## Contributing

You can contribute to this project by opening an issue or creating a pull request on [GitHub](https://github.com/beiyuouo/awesome-asynchronous-federated-learning).

Add paper to the `papers.yaml` file with the following format:

```yaml

- title: "Communication-Efficient Learning of Deep Networks from Decentralized Data"

  abbr: FedAvg

  year: 2016

  conf: AISTAT

  links:

    PDF: https://arxiv.org/abs/1602.05629.pdf

    GitHub:

```

## Citations

```text

@misc{awesomeafl,

    title = {awesome-asyncrhonous-federated-learning},

    author = {Bingjie Yan},

    year = {2022},

    howpublished = {\\url{https://github.com/beiyuouo/awesome-asynchronous-federated-learning}

}

```