Multi-dimensional Fair Federated Learning

TL;DR

This paper introduces mFairFL, a federated learning method that ensures both group and client fairness by detecting and mitigating gradient conflicts, improving fairness without sacrificing model performance.

Contribution

The paper presents mFairFL, a novel federated learning approach that achieves simultaneous group and client fairness through conflict detection and gradient curation.

Findings

mFairFL outperforms seven baselines on benchmark datasets.

Theoretical analysis confirms fairness improvements.

Gradient conflict mitigation enhances model fairness.

Abstract

Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data without compromising privacy. Group fairness and client fairness are two dimensions of fairness that are important for FL. Standard FL can result in disproportionate disadvantages for certain clients, and it still faces the challenge of treating different groups equitably in a population. The problem of privately training fair FL models without compromising the generalization capability of disadvantaged clients remains open. In this paper, we propose a method, called mFairFL, to address this problem and achieve group fairness and client fairness simultaneously. mFairFL leverages differential multipliers to construct an optimization objective for empirical risk minimization with fairness constraints. Before aggregating locally trained models, it first detects conflicts among their gradients, and then iteratively curates the direction and magnitude of gradients to mitigate these conflicts. Theoretical analysis proves mFairFL facilitates the fairness in model development. The experimental evaluations based on three benchmark datasets show significant advantages of mFairFL compared to seven state-of-the-art baselines.