Client Selection in Federated Learning: Principles, Challenges, and Opportunities
This is an incremental review paper that helps practitioners and researchers understand and apply client selection methods to improve federated learning systems.
The paper addresses the problem of client heterogeneity in federated learning, which can lead to lower model accuracy and slower convergence, by reviewing existing client selection algorithms that show promising performance improvements.
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 paper, 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.