Emulating Full Participation: An Effective and Fair Client Selection Strategy for Federated Learning

TL;DR

This paper introduces a novel client selection strategy for federated learning that balances model performance and fairness by considering their complex interactions and promoting data diversity among selected clients.

Contribution

It formulates client selection as a long-term optimization problem using Lyapunov functions and submodularity, effectively improving both fairness and performance.

Findings

Improved model accuracy and fairness metrics

Achieved convergence comparable to full client participation

Enhanced data diversity among selected clients

Abstract

In federated learning, client selection is a critical problem that significantly impacts both model performance and fairness. Prior studies typically treat these two objectives separately, or balance them using simple weighting schemes. However, we observe that commonly used metrics for model performance and fairness often conflict with each other, and a straightforward weighted combination is insufficient to capture their complex interactions. To address this, we first propose two guiding principles that directly tackle the inherent conflict between the two metrics while reinforcing each other. Based on these principles, we formulate the client selection problem as a long-term optimization task, leveraging the Lyapunov function and the submodular nature of the problem to solve it effectively. Experiments show that the proposed method improves both model performance and fairness, guiding the system to converge comparably to full client participation. This improvement can be attributed to the fact that both model performance and fairness benefit from the diversity of the selected clients' data distributions. Our approach adaptively enhances this diversity by selecting clients based on their data distributions, thereby improving both model performance and fairness.