BoostFGL: Boosting Fairness in Federated Graph Learning

TL;DR

BoostFGL introduces a boosting framework for federated graph learning that enhances fairness by addressing label skew, topology confounding, and update dilution, leading to significant fairness improvements without sacrificing overall accuracy.

Contribution

The paper presents BoostFGL, a novel boosting-style framework that systematically improves fairness in federated graph learning through coordinated client-side and server-side mechanisms.

Findings

BoostFGL improves fairness by 8.43% in Overall-F1.

It maintains competitive overall performance.

Extensive experiments on 9 datasets validate its effectiveness.

Abstract

Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods often achieve high overall accuracy, we show that this average performance can conceal severe degradation on disadvantaged node groups. From a fairness perspective, these disparities arise systematically from three coupled sources: label skew toward majority patterns, topology confounding in message propagation, and aggregation dilution of updates from hard clients. To address this, we propose \textbf{BoostFGL}, a boosting-style framework for fairness-aware FGL. BoostFGL introduces three coordinated mechanisms: \ding{182} \emph{Client-side node boosting}, which reshapes local training signals to emphasize systematically under-served nodes; \ding{183} \emph{Client-side topology boosting}, which reallocates propagation emphasis toward reliable yet underused structures and attenuates misleading neighborhoods; and \ding{184} \emph{Server-side model boosting}, which performs difficulty- and reliability-aware aggregation to preserve informative updates from hard clients while stabilizing the global model. Extensive experiments on 9 datasets show that BoostFGL delivers substantial fairness gains, improving Overall-F1 by 8.43\%, while preserving competitive overall performance against strong FGL baselines.