FairAGG: Toward Fair Graph Neural Networks via Fair Aggregation

Graph neural networks (GNNs) have shown intrinsic topology bias inherited from graph-structured data, where a majority of nodes are associated with specific sensitive attributes (e.g., age, and race). In this regard, GNNs make discriminatory decisions toward certain groups defined by the sensitive attribute. Over the past few years, efforts have been made to mitigate the fairness issue of GNNs caused by topology bias. While achieving impressive results, these works likely only scratch the surface of what is possible with well-tuned GNN models or heuristic graph preprocessing techniques. Despite modern GNNs being built upon the message-passing framework, few works dig into the hidden reasoning behind the fairness issue of GNNs from such a fundamental perspective. In this work, we empirically demonstrate that message aggregation with higher edge weight for intergroup edges improves model fairness but sacrifices utility. The above observations motivate us to propose and derive a simple yet effective message-passing scheme, FairAGG, leading to more fair GNNs with less comprised downstream performance. Specifically, FairAGG measures the contribution of graph topology on fairness using Shapley value, which facilitates fair aggregation through reweighting. Experiments on several real-world datasets demonstrate that FairAGG enhances the fairness of the GNNs model while maintaining competitive utility performance.