面向公平图神经网络的子图过滤

中文摘要 AI 辅助

图神经网络（GNNs）即便在节点特征中排除敏感属性，也可能表现出不公平行为，因为图拓扑结构和消息传递会在敏感同质性下传播与群体相关的信号。现有感知公平性的GNN方法主要在全局层面约束表示或预测分布，未明确控制聚合过程中偏见信息传播的局部结构路径。我们提出面向公平图神经网络的子图过滤（SF-GNN），这是一个轻量级、与架构无关的框架，从源头缓解结构偏见。SF-GNN通过结合敏感同质性与结构传播放大器（包括枢纽节点参与和三元闭包）识别易产生偏见的边，随后在每个消息传递步骤中引入随机边过滤，选择性降低这些边的权重或移除它们，同时保留剩余图结构。训练过程中还结合带有预热调度的统计均等正则化器以稳定优化。在五个基准数据集上的实验表明，SF-GNN在保持竞争力预测性能的同时实现了一致的公平性提升，相较于近期感知公平性的GNN基线，实现了更优的公平性-准确率权衡。

英文摘要

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.

发表机构

• Molly Wardaguga Institute for First Nations Birth Rights, Charles Darwin University（查尔斯·达尔文大学莫莉·瓦达古加原住民生育权研究所）
• The University of Sydney（悉尼大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

ICONIP 2026