Asynchronous Federated Learning

Asynchronous federated learning (AFL) aims to improve the efficiency and scalability of federated learning by allowing clients to update a shared model independently and at their own pace, rather than synchronously. Current research focuses on addressing challenges like staleness of updates, heterogeneity in client resources and data distributions, and robustness against Byzantine failures, often employing techniques such as buffered aggregation, gradient compression, and adaptive client selection. These advancements enhance the practicality of federated learning for resource-constrained and decentralized environments, with applications ranging from IoT networks and autonomous driving to geo-distributed systems and satellite constellations.

Papers

December 23, 2023

Efficient Asynchronous Federated Learning with Sparsification and Quantization
Juncheng Jia, Ji Liu, Chendi Zhou, Hao Tian, Mianxiong Dong, Dejing Dou
Quantization Operator Random Sparsification Asynchronous Federated Learning Asynchronous Execution

December 16, 2023

Take History as a Mirror in Heterogeneous Federated Learning
Xiaorui Jiang, Hengwei Xu, Yu Gao, Yong Liao, Pengyuan Zhou
Federated Learning Heterogeneous Federated Learning Historical Text Asynchronous Federated Learning Etruscan Mirror Convergence Performance Stale Gradient

November 28, 2023

Asynchronous Wireless Federated Learning with Probabilistic Client Selection
Jiarong Yang, Yuan Liu, Fangjiong Chen, Wen Chen, Changle Li
Federated Learning Convergence Rate Client Selection Asynchronous Federated Learning

October 10, 2023

Asynchronous Federated Learning with Incentive Mechanism Based on Contract Theory
Danni Yang, Yun Ji, Zhoubin Kou, Xiaoxiong Zhong, Sheng Zhang
Asynchronous Federated Learning Incentive Mechanism Contract Theory Asynchronous Aggregation

August 25, 2023

DAG-ACFL: Asynchronous Clustered Federated Learning based on DAG-DLT
Xiaofeng Xue, Haokun Mao, Qiong Li
Asynchronous Federated Learning Dag DLT FL Framework

August 1, 2023

Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation
Tomas Ortega, Hamid Jafarkhani
Asynchronous Federated Learning Quantization Error Asynchronous Aggregation

June 21, 2023

Timely Asynchronous Hierarchical Federated Learning: Age of Convergence
Purbesh Mitra, Sennur Ulukus
Federated Learning Early Stage Convergence Speech Based Age Model Aggregation Asynchronous Federated Learning Edge Cloud Dense Environment Training Iteration

May 25, 2023

FAVANO: Federated AVeraging with Asynchronous NOdes
Louis Leconte, Van Minh Nguyen, Eric Moulines
Deep Neural Network Convergence Guarantee Federated Averaging Asynchronous Federated Learning Asynchronous Architecture

May 22, 2023

Asynchronous Multi-Model Dynamic Federated Learning over Wireless Networks: Theory, Modeling, and Optimization
Zhan-Lun Chang, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
Machine Learning Optimization Purpose Theoretical Understanding Wireless Network Convergence Guarantee Asynchronous Federated Learning Asynchronous Update Runtime Elastic Tensor Selection

April 14, 2023

TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training
Tuo Zhang, Lei Gao, Sunwoo Lee, Mi Zhang, Salman Avestimehr
Asynchronous Federated Learning Cross Device Federated Learning Slow Convergence Stale Gradient Partial Model Training

April 6, 2023

Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing
Qiong Wu, Siyuan Wang, Pingyi Fan, Qiang Fan
Vehicular Network Asynchronous Federated Learning Vehicular Edge Computing

April 4, 2023

Online Learning with Adversaries: A Differential-Inclusion Analysis
Swetha Ganesh, Alexandre Reiffers-Masson, Gugan Thoppe
Online Learning Lyapunov Function Asynchronous Federated Learning Adversary Agent Global Attractor Matrix Variate Stopping Time

March 27, 2023

Asynchronous Online Federated Learning with Reduced Communication Requirements
Francois Gauthier, Vinay Chakravarthi Gogineni, Stefan Werner, Yih-Fang Huang, Anthony Kuh
Asynchronous Federated Learning Random Participation Computational Power Communication Cost

January 17, 2023

Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks
Xiaofan Yu, Ludmila Cherkasova, Harsh Vardhan, Quanling Zhao, Emily Ekaireb, Xiyuan Zhang, Arya Mazumdar, Tajana Rosing
Internet of Thing Internet of Thing Network Asynchronous Federated Learning Device Learning

December 22, 2022

AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms
Mohamed Elmahallawy, Tie Luo
Asynchronous Federated Learning Network Topology Low Earth Orbit Straggler Mitigation Propagation Delay Hierarchically Fusing Satellite High Altitude Platform

December 14, 2022

Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks
Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson
Wireless Network Task Scheduling Asynchronous Federated Learning Device Training Collaborative Machine Learning Aggregation Method Limited Network

December 13, 2022

AFLGuard: Byzantine-robust Asynchronous Federated Learning
Minghong Fang, Jia Liu, Neil Zhenqiang Gong, Elizabeth S. Bentley
Asynchronous Federated Learning Byzantine Robust Byzantine Robust Federated Learning Byzantine Fault

November 22, 2022

GitFL: Adaptive Asynchronous Federated Learning using Version Control
Ming Hu, Zeke Xia, Zhihao Yue, Jun Xia, Yihao Huang, Yang Liu, Mingsong Chen
Asynchronous Federated Learning Dual Branch Version Control Model Versioning

November 14, 2022

FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity
Mingjie Wang, Jianxiong Guo, Weijia Jia
Curriculum Learning Asynchronous Federated Learning Heterogeneous User Domain Informed Neural Network Model Drift

October 28, 2022

Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout
Chen Dun, Mirian Hipolito, Chris Jermaine, Dimitrios Dimitriadis, Anastasios Kyrillidis
High Efficiency Structured Dropout Asynchronous Federated Learning Asynchronous Learning Asynchronous Approach

Asynchronous Federated Learning

Papers

Efficient Asynchronous Federated Learning with Sparsification and Quantization

Take History as a Mirror in Heterogeneous Federated Learning

Asynchronous Wireless Federated Learning with Probabilistic Client Selection

Asynchronous Federated Learning with Incentive Mechanism Based on Contract Theory

DAG-ACFL: Asynchronous Clustered Federated Learning based on DAG-DLT

Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation

Timely Asynchronous Hierarchical Federated Learning: Age of Convergence

FAVANO: Federated AVeraging with Asynchronous NOdes

Asynchronous Multi-Model Dynamic Federated Learning over Wireless Networks: Theory, Modeling, and Optimization

TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training

Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing

Online Learning with Adversaries: A Differential-Inclusion Analysis

Asynchronous Online Federated Learning with Reduced Communication Requirements

Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks

AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platforms

Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks

AFLGuard: Byzantine-robust Asynchronous Federated Learning

GitFL: Adaptive Asynchronous Federated Learning using Version Control

FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity

Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout