Submodular Maximization Approaches for Equitable Client Selection in Federated Learning

TL;DR

This paper proposes two submodular maximization methods, SUBTRUNC and UNIONFL, to improve fairness in client selection for federated learning, demonstrating significant fairness improvements through theoretical guarantees and extensive evaluations.

Contribution

Introduces novel submodular-based client selection algorithms, SUBTRUNC and UNIONFL, to enhance fairness in federated learning, with proven convergence guarantees and empirical validation.

Findings

Significant fairness improvements demonstrated in heterogeneous scenarios

Theoretical convergence guarantees provided for both methods

Empirical evaluations show balanced client performance

Abstract

In a conventional Federated Learning framework, client selection for training typically involves the random sampling of a subset of clients in each iteration. However, this random selection often leads to disparate performance among clients, raising concerns regarding fairness, particularly in applications where equitable outcomes are crucial, such as in medical or financial machine learning tasks. This disparity typically becomes more pronounced with the advent of performance-centric client sampling techniques. This paper introduces two novel methods, namely SUBTRUNC and UNIONFL, designed to address the limitations of random client selection. Both approaches utilize submodular function maximization to achieve more balanced models. By modifying the facility location problem, they aim to mitigate the fairness concerns associated with random selection. SUBTRUNC leverages client loss information to diversify solutions, while UNIONFL relies on historical client selection data to ensure a more equitable performance of the final model. Moreover, these algorithms are accompanied by robust theoretical guarantees regarding convergence under reasonable assumptions. The efficacy of these methods is demonstrated through extensive evaluations across heterogeneous scenarios, revealing significant improvements in fairness as measured by a client dissimilarity metric.