FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphs

TL;DR

FairGFL introduces a privacy-preserving federated learning algorithm that addresses fairness issues caused by imbalanced overlapping subgraphs in graph data, improving both fairness and utility.

Contribution

The paper presents FairGFL, a novel algorithm that enhances fairness in graph federated learning with overlapping subgraphs while preserving privacy and maintaining model utility.

Findings

FairGFL outperforms baseline algorithms in fairness metrics.

FairGFL achieves higher model utility compared to existing methods.

The approach effectively mitigates unfairness caused by data overlap imbalance.

Abstract

Graph federated learning enables the collaborative extraction of high-order information from distributed subgraphs while preserving the privacy of raw data. However, graph data often exhibits overlap among different clients. Previous research has demonstrated certain benefits of overlapping data in mitigating data heterogeneity. However, the negative effects have not been explored, particularly in cases where the overlaps are imbalanced across clients. In this paper, we uncover the unfairness issue arising from imbalanced overlapping subgraphs through both empirical observations and theoretical reasoning. To address this issue, we propose FairGFL (FAIRness-aware subGraph Federated Learning), a novel algorithm that enhances cross-client fairness while maintaining model utility in a privacy-preserving manner. Specifically, FairGFL incorporates an interpretable weighted aggregation approach to enhance fairness across clients, leveraging privacy-preserving estimation of their overlapping ratios. Furthermore, FairGFL improves the tradeoff between model utility and fairness by integrating a carefully crafted regularizer into the federated composite loss function. Through extensive experiments on four benchmark graph datasets, we demonstrate that FairGFL outperforms four representative baseline algorithms in terms of both model utility and fairness.