Minimax Demographic Group Fairness in Federated Learning

TL;DR

This paper introduces FedMinMax, an algorithm for achieving minimax demographic group fairness in federated learning, addressing the challenge of partial group access among participants and demonstrating superior fairness performance.

Contribution

The paper proposes a novel group fairness objective for federated learning, along with FedMinMax, an optimization algorithm with performance guarantees, and provides empirical evidence of its effectiveness.

Findings

FedMinMax achieves superior group fairness compared to existing methods.

The approach maintains performance guarantees similar to centralized algorithms.

Experimental results show competitive or better fairness in various setups.

Abstract

Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how our proposed group fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm -- FedMinMax -- for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other state-of-the-art methods in terms of group fairness in various federated learning setups, showing that our approach exhibits competitive or superior performance.