Client Selection in Federated Learning: Principles, Challenges, and Opportunities

As a privacy-preserving paradigm for training machine learning (ML) models, federated learning (FL) has received tremendous attention from both industry and academia. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. Thus, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement. In this article, we systematically present recent advances in the emerging field of FL client selection and its challenges and research opportunities. We hope to facilitate practitioners in choosing the most suitable client selection mechanisms for their applications, as well as inspire researchers and newcomers to better understand this exciting research topic.

I. Introduction

Federated learning (FL) has gained great momentum in both academia and industry [1], [2]. As a decentralized paradigm that preserves data privacy while enabling machine learning (ML) model training, FL has been applied to various fields, such as next-word prediction [3], financial fraud detection [4], and healthcare data analysis [5]. According to the POLARIS report, the global FL market was valued at USD 110.8 million in 2021 and is expected to grow at a compound annual growth rate of 10.7%, reaching USD 266.8 million by 2030 [6].