Awesome Asynchronous Federated Learning

[GitHub] [Web]

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 11:33:01

Fully Asynchronous

2022

• [AsyncFedED] AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation (arXiv) [PDF]

2021

• [FedSA] FedSA: A staleness-aware asynchronous Federated Learning algorithm with non-IID data (FGCS Elsevier) [PDF]
• [FedDR] FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization (ResearchGate) [PDF]
• An Asynchronous Federated Learning Approach for a Security Source Code Scanner (ICISSP) [PDF]
• [FedConD] Asynchronous Federated Learning for Sensor Data with Concept Drift (arXiv) [PDF]

2020

• Adaptive Task Allocation for Asynchronous Federated and Parallelized Mobile Edge Learning (arXiv) [PDF]
• [ASO-Fed] Asynchronous Online Federated Learning for Edge Devices with Non-IID Data (Big Data) [PDF]

2019

• [FedAsync] Asynchronous Federated Optimization (OPT) [PDF] [Code]
• [DP-AFL] Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics (TII) [PDF]
• [TWAFL] Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation (TNNLS) [PDF]

2018

• Federated learning for ultra-reliable low-latency V2V communications (GLOBECOM) [PDF]

K-Asynchronous or Semi-Asynchronous

2022

• [KAFL] KAFL: Achieving High Training Efficiency for Fast-K Asynchronous Federated Learning (ICDCS) [PDF]
• [WKAFL] Towards Efficient and Stable K-Asynchronous Federated Learning With Unbounded Stale Gradients on Non-IID Data (IEEE TPDS) [PDF]
• [FedBuff] Federated Learning with Buffered Asynchronous Aggregation (AISTATS) [PDF]

2021

• [FedSA] FedSA: A Semi-Asynchronous Federated Learning Mechanism in Heterogeneous Edge Computing (IEEE JSAC) [PDF]
• [SAFA] SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead (IEEE Transactions on Computers) [PDF]

Privacy-Preserving

2021

• [AFSGD-VP] Privacy-Preserving Asynchronous Vertical Federated Learning Algorithms for Multiparty Collaborative Learning (TNNLS) [PDF]

Hierarchical or Tier-based

2023

• [TimelyFL] TimelyFL: Heterogeneity-Aware Asynchronous Federated Learning With Adaptive Partial Training (CVPR) [PDF]
• [AHFL] Timely Asynchronous Hierarchical Federated Learning: Age of Convergence (arXiv) [PDF]
• [HiFlash] HiFlash: Communication-Efficient Hierarchical Federated Learning With Adaptive Staleness Control and Heterogeneity-Aware Client-Edge Association (T-PDS) [PDF]
• Scheduling and Aggregation Design for Asynchronous Federated Learning Over Wireless Networks (IEEE JSAC) [PDF]

2022

• Client-Edge-Cloud Hierarchical Federated Learning (IEEE/ACM SEC) [PDF]
• Hierarchical Federated Learning With Quantization: Convergence Analysis and System Design (IEEE TWC) [PDF]

2021

• Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients (arXiv) [PDF]
• Time Minimization in Hierarchical Federated Learning (arXiv) [PDF]
• [FedAT] FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers (arXiv) [PDF]

2020

• [TiFL] TiFL: A Tier-based Federated Learning System (HPDC) [PDF]

Model Heterogeneous

2023

• [MA-FL] Asynchronous Multi-Model Federated Learning over Wireless Networks: Theory, Modeling, and Optimization (arXiv) [PDF]

Fairness

2022

• Client Selection for Asynchronous Federated Learning with Fairness Consideration (ICC Workshop) [PDF]
• Online Client Selection for Asynchronous Federated Learning With Fairness Consideration (IEEE TWC) [PDF]

Continual Learning

2023

• [AFCL] Asynchronous Federated Continual Learning (CVPR FedVision Workshop) [PDF] [Code]

Vertical Asynchronous Federated Learning

2021

• [AFSGD-VP] Privacy-Preserving Asynchronous Vertical Federated Learning Algorithms for Multiparty Collaborative Learning (TNNLS) [PDF]

2020

• [VAFL] VAFL: a Method of Vertical Asynchronous Federated Learning (ICML 2020) [PDF]

Asynchronous Increment Federated Learning

2020

• [VAFL] VAFL: a Method of Vertical Asynchronous Federated Learning (ICML 2020) [PDF]

Application

2018

• Asynchronous Federated Learning for Geospatial Applications (ECML PKDD) [PDF]

General Federated Learning

• [FedAvg] Communication-Efficient Learning of Deep Networks from Decentralized Data (AISTATS) [PDF]

Benchmarks

• [LEAF] Leaf: A benchmark for federated settings (arXiv) [PDF] [GitHub]

Libraries(Which support Asynchronous Federated Learning)

• [FedML] FedML: A Research Library and Benchmark for Federated Machine Learning (arXiv) [Home] [PDF] [GitHub] [Docs]
• [FedHF] FedHF: 🔨 A Flexible Federated Learning Simulator. [GitHub]
• [FederatedScope] FederatedScope: A Flexible Federated Learning Platform for Heterogeneity [Home] [GitHub] [PDF]
• [PySyft] PySyft: A Library for Easy Federated Learning (Studies in Computational Intelligence) [GitHub] [PDF]
• [FedLab] FedLab: A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research. [GitHub] [Docs]

Survey

• [Open Problem] Advances and Open Problems in Federated Learning (FnTML) [PDF]
• Asynchronous Federated Learning on Heterogeneous Devices: A Survey (arXiv) [PDF]

Theory

• On the Convergence of FedAvg on Non-IID Data (ICLR 2020) [PDF] [GitHub]

Heterogeneous

• [FedProx] Federated Optimization in Heterogeneous Networks (MLSys 2020) [PDF] [GitHub]
• [FedBN] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization (ICLR 2021) [PDF] [GitHub]
• [Pisces] Pisces: Efficient Federated Learning via Guided Asynchronous Training (ACM SoCC 2022) [PDF] [GitHub]

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.

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

- 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

@misc{awesomeafl,
    title = {awesome-asyncrhonous-federated-learning},
    author = {Bingjie Yan},
    year = {2022},
    howpublished = {\\url{https://github.com/beiyuouo/awesome-asynchronous-federated-learning}
}