Client Participation

Client participation in federated learning (FL) focuses on optimizing the selection and engagement of clients to improve model accuracy, efficiency, and fairness while respecting resource constraints and data heterogeneity. Current research emphasizes developing algorithms that address issues like non-uniform and correlated client participation, incomplete participation, and the impact of client dropout, often employing techniques such as variance reduction, client filtering, and weighted aggregation strategies within frameworks like FedAvg and its variants. These advancements are crucial for enabling practical, large-scale FL deployments across diverse settings, particularly in resource-limited environments like mobile devices or healthcare institutions, and for ensuring robust and unbiased model training.

Papers

October 30, 2024

Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
Michael Crawshaw, Mingrui Liu
Raw Data User Behavior Communication Efficient Nonconvex Optimization Communication Complexity Heterogeneous Setting Client Availability Client Participation

October 2, 2024

Debiasing Federated Learning with Correlated Client Participation
Zhenyu Sun, Ziyang Zhang, Zheng Xu, Gauri Joshi, Pranay Sharma, Ermin Wei
Federated Averaging Cross Device Federated Learning Optimal Separation Client Participation

June 21, 2024

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
Sunwoo Lee, Tuo Zhang, Saurav Prakash, Yue Niu, Salman Avestimehr
Federated Learning Embracing CompAct Client Participation Partial Model Training

May 22, 2024

Emulating Full Client Participation: A Long-Term Client Selection Strategy for Federated Learning
Qingming Li, Juzheng Miao, Puning Zhao, Li Zhou, Shouling Ji, Bowen Zhou, Furui Liu
Client Selection Convergence Performance Client Participation

May 4, 2024

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
Haibo Yang, Peiwen Qiu, Prashant Khanduri, Minghong Fang, Jia Liu
Federated Learning Speech Presence Federated Averaging PAC Learnability Client Participation

April 20, 2024

EHRFL: Federated Learning Framework for Institution-Specific Model Construction using Electronic Health Records
Jiyoun Kim, Junu Kim, Kyunghoon Hur, Edward Choi
Federated Learning Electronic Health Record Intermediate Latent Client Participation Specific Model Heterogeneous Electronic Health Record

October 11, 2023

Advocating for the Silent: Enhancing Federated Generalization for Non-Participating Clients
Zheshun Wu, Zenglin Xu, Dun Zeng, Qifan Wang, Jie Liu
Federated Learning Generalization Bound Generalization Gap Training Distribution Client Participation Information Theoretic Generalization

April 17, 2023

Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation
Bing Luo, Yutong Feng, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
Federated Learning Incentive Mechanism Incentive Mechanism Design Client Participation

February 13, 2023

FilFL: Client Filtering for Optimized Client Participation in Federated Learning
Fares Fourati, Salma Kharrat, Vaneet Aggarwal, Mohamed-Slim Alouini, Marco Canini
Faster Convergence Online Filtering Machine Learning Paradigm Client Participation

February 7, 2023

Federated Learning with Regularized Client Participation
Grigory Malinovsky, Samuel Horváth, Konstantin Burlachenko, Peter Richtárik
Convergence Rate FedAvg Algorithm Client Sampling Client Participation

February 6, 2023

On the Convergence of Federated Averaging with Cyclic Client Participation
Yae Jee Cho, Pranay Sharma, Gauri Joshi, Zheng Xu, Satyen Kale, Tong Zhang
Early Stage Convergence Convergence Rate Federated Averaging FedAvg Converges Client Participation

October 3, 2022

Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests
Chih-Fan Hsu, Ming-Ching Chang, Wei-Chao Chen
Differential Privacy Client Participation Fragmented Personal Data

July 28, 2022

FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning
Divyansh Jhunjhunwala, Pranay Sharma, Aushim Nagarkatti, Gauri Joshi
Variance Reduction Local Optimization Client Participation Data Variance

June 13, 2022

Anchor Sampling for Federated Learning with Partial Client Participation
Feijie Wu, Song Guo, Zhihao Qu, Shiqi He, Ziming Liu, Jing Gao
Client Participation Partial Participation

May 31, 2022

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
Alexander Tyurin, Peter Richtárik
Optimization Purpose Stochastic Gradient Variance Reduction Communication Efficient Communication Complexity Client Participation Oracle Complexity Nonconvex Nonconcave Problem

May 26, 2022

Client Participation

Papers

Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis

Debiasing Federated Learning with Correlated Client Participation

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training

Emulating Full Client Participation: A Long-Term Client Selection Strategy for Federated Learning

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

EHRFL: Federated Learning Framework for Institution-Specific Model Construction using Electronic Health Records

Advocating for the Silent: Enhancing Federated Generalization for Non-Participating Clients

Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation

FilFL: Client Filtering for Optimized Client Participation in Federated Learning

Federated Learning with Regularized Client Participation

On the Convergence of Federated Averaging with Cyclic Client Participation

Mitigating Data Absence in Federated Learning Using Privacy-Controllable Data Digests

FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning

Anchor Sampling for Federated Learning with Partial Client Participation

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting

A Unified Analysis of Federated Learning with Arbitrary Client Participation

Combating Client Dropout in Federated Learning via Friend Model Substitution