Achieving Fairness Across Local and Global Models in Federated Learning

TL;DR

This paper introduces quiFL novel federated learning method that enhances both local and global fairness across diverse clients, balancing accuracy and fairness while preventing bias propagation, validated through extensive experiments and real-world healthcare data.

Contribution

The paper presents quiFL new approach that incorporates fairness into local optimization and coordination, improving fairness and performance distribution in federated learning.

Findings

quiFLchieves better local fairness and accuracy balance.

It ensures global fairness and uniform performance among clients.

Demonstrated effectiveness on healthcare dataset across hospital locations.

Abstract

Achieving fairness across diverse clients in Federated Learning (FL) remains a significant challenge due to the heterogeneity of the data and the inaccessibility of sensitive attributes from clients' private datasets. This study addresses this issue by introducing \texttt{EquiFL}, a novel approach designed to enhance both local and global fairness in federated learning environments. \texttt{EquiFL} incorporates a fairness term into the local optimization objective, effectively balancing local performance and fairness. The proposed coordination mechanism also prevents bias from propagating across clients during the collaboration phase. Through extensive experiments across multiple benchmarks, we demonstrate that \texttt{EquiFL} not only strikes a better balance between accuracy and fairness locally at each client but also achieves global fairness. The results also indicate that \texttt{EquiFL} ensures uniform performance distribution among clients, thus contributing to performance fairness. Furthermore, we showcase the benefits of \texttt{EquiFL} in a real-world distributed dataset from a healthcare application, specifically in predicting the effects of treatments on patients across various hospital locations.