Client Sampling

Client sampling in federated learning (FL) focuses on efficiently selecting a subset of clients for model training in each round, addressing communication bottlenecks and data heterogeneity across devices. Current research emphasizes developing adaptive sampling strategies that consider both statistical (data distribution) and system (communication bandwidth, computation capacity) heterogeneity, often employing techniques like clustering, online learning, and variance reduction to improve convergence speed and model accuracy. These advancements are crucial for making FL practical in large-scale deployments, enhancing privacy preservation, and improving the efficiency of distributed machine learning applications.

Papers

May 25, 2024

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing
Yongxin Guo, Lin Wang, Xiaoying Tang, Tao Lin
Client Sampling

May 3, 2024

Towards Fairness in Provably Communication-Efficient Federated Recommender Systems
Kirandeep Kaur, Sujit Gujar, Shweta Jain
Recommender System Procedural Fairness Centralized Machine Learning Sample Complexity Bound Client Sampling

April 22, 2024

Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks
Bing Luo, Wenli Xiao, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas
Wireless Network Client Sampling Convergence Time Bandwidth Allocation

February 20, 2024

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
Youssef Allouah, Sadegh Farhadkhani, Rachid GuerraouI, Nirupam Gupta, Rafael Pinot, Geovani Rizk, Sasha Voitovych
Global Impact Adversarial Behavior Local Context Byzantine Robust Federated Learning Client Sampling

February 15, 2024

Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling
Jiaxiang Geng, Yanzhao Hou, Xiaofeng Tao, Juncheng Wang, Bing Luo
Sampling Technique Client Sampling Adaptive Federated Learning Independent Sampling Heterogeneous Wireless Network Faster Client

February 8, 2024

Asynchronous Diffusion Learning with Agent Subsampling and Local Updates
Elsa Rizk, Kun Yuan, Ali H. Sayed
Practical Algorithm Global Model Local Context Client Sampling Asynchronous Learning Local Datasets

January 29, 2024

Cross-silo Federated Learning with Record-level Personalized Differential Privacy
Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng
Differential Privacy Privacy Budget Cross Silo Federated Learning Client Sampling

December 29, 2023

LEFL: Low Entropy Client Sampling in Federated Learning
Waqwoya Abebe, Pablo Munoz, Ali Jannesari
Uniform Sampling Sampling Strategy Data Balancing Client Sampling

November 23, 2023

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
Machine Learning Model Variance Reduction Byzantine Robust Client Sampling Gradient Clipping Byzantine Fault Tolerance Partial Participation Byzantine Robust Method

October 4, 2023

Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance
Dun Zeng, Zenglin Xu, Yu Pan, Xu Luo, Qifan Wang, Xiaoying Tang
Federated Optimization Client Sampling

September 30, 2023

Accelerating Non-IID Federated Learning via Heterogeneity-Guided Client Sampling
Huancheng Chen, Haris Vikalo
Client Selection Statistical Heterogeneity Client Sampling Federated Learning Client Based Sampling

June 22, 2023

Adaptive Compression in Federated Learning via Side Information
Berivan Isik, Francesco Pase, Deniz Gunduz, Sanmi Koyejo, Tsachy Weissman, Michele Zorzi
Side Information Client Sampling Adaptive Compression Sign Based Compression Overall Compression

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

January 25, 2023

When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning
Wenkai Yang, Yankai Lin, Guangxiang Zhao, Peng Li, Jie Zhou, Xu Sun
Learning Rate Client Sampling Aggregated Gradient Server Learning Rate

December 3, 2022

GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning
Shiqi He, Qifan Yan, Feijie Wu, Lanjun Wang, Mathias Lécuyer, Ivan Beschastnikh
Model Compression Masked Modeling Client Sampling Phonetically Noised Glue Federated Learning Client

November 25, 2022

FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Haibing Jin, Peizhen Yang, Siqi Shen, Cheng Wang
Federated Prompt Cooperation Unbiased Learning Client Sampling Client Availability Graph Sampling

September 30, 2022

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
Jianyi Zhang, Ang Li, Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Changyou Chen, Yiran Chen, Hai Li
Class Imbalance Homomorphic Encryption Client Sampling Random Selection Balanced Sampling

September 15, 2022

UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs
Yunyi Yang, Hong Ding, Qingyi Liu, Xiaojun Quan
Task Oriented Task Oriented Dialog System Client Sampling Task Oriented Dialog Exposure Bias

May 27, 2022

DELTA: Diverse Client Sampling for Fasting Federated Learning
Lin Wang, YongXin Guo, Tao Lin, Xiaoying Tang
Delta XAI Client Sampling Unbiased Sampling Client Gradient

December 28, 2021

Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
Boxin Zhao, Lingxiao Wang, Mladen Kolar, Ziqi Liu, Zhiqiang Zhang, Jun Zhou, Chaochao Chen
Gradient Descent Online Learning Bandit Feedback Coordinate Descent Stochastic Mirror Descent Client Sampling

Client Sampling

Papers

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing

Towards Fairness in Provably Communication-Efficient Federated Recommender Systems

Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates

Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling

Asynchronous Diffusion Learning with Agent Subsampling and Local Updates

Cross-silo Federated Learning with Record-level Personalized Differential Privacy

LEFL: Low Entropy Client Sampling in Federated Learning

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences

Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance

Accelerating Non-IID Federated Learning via Heterogeneity-Guided Client Sampling

Adaptive Compression in Federated Learning via Side Information

Federated Learning with Regularized Client Participation

When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning

GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning

FedGS: Federated Graph-based Sampling with Arbitrary Client Availability

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs

DELTA: Diverse Client Sampling for Fasting Federated Learning

Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback