Subgraph Filtering for Fair Graph Neural Networks

2026-08-26

AI Summary

为解决图神经网络中的不公平问题，SF-GNN通过识别并过滤具有偏见倾向的边来控制局部结构路径上的信息传播，同时保持预测性能。

Abstract

Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features, because graph topology and message passing propagate group-correlated signals under sensitive homophily. Existing fairness-aware GNN methods mainly constrain representations or prediction distributions at a global level, without explicitly controlling the local structural pathways through which biased information propagates during aggregation. We propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a lightweight and architecture-agnostic framework that mitigates structural bias at its source. SF-GNN identifies bias-prone edges by combining sensitive homophily with structural propagation amplifiers, including hub participation and triadic closure. It then incorporates stochastic edge filtering into each message-passing step to selectively downweight or remove these edges while preserving the remaining graph structure. Training further incorporates a statistical-parity regularizer with a warm-up schedule to stabilize optimization. Experiments on five benchmark datasets show that SF-GNN achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness--accuracy trade-off than recent fairness-aware GNN baselines.

Problem

• Graph Neural Networks
• Fairness
• Sensitive Homophily
• Structural Bias
• Message Passing

Innovation

• Subgraph Filtering
• Sensitive Homophily
• Structural Propagation Amplifiers
• Stochastic Edge Filtering
• Statistical-Parity Regularizer