FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning
Renqiang Luo, Huafei Huang, Ivan Lee, Chengpei Xu, Jianzhong Qi, Feng Xia
TL;DR
FairGP tackles fairness deficiencies in Graph Transformer models while addressing scalability on large graphs. It introduces a fairness-aware pipeline that partitions the graph, augments node features with a structure-based matrix, and zeros inter-cluster attention to curb the spillover of higher-order node bias. Theoretical results bound sensitive-feature similarity by cross-cluster attention, and empirical results on six real-world datasets show that FairGP improves fairness metrics with competitive utility and reduced training cost. The approach offers a practical path toward fair and scalable GTs for real-world applications where sensitive attributes must be handled with care.
Abstract
Recent studies have highlighted significant fairness issues in Graph Transformer (GT) models, particularly against subgroups defined by sensitive features. Additionally, GTs are computationally intensive and memory-demanding, limiting their application to large-scale graphs. Our experiments demonstrate that graph partitioning can enhance the fairness of GT models while reducing computational complexity. To understand this improvement, we conducted a theoretical investigation into the root causes of fairness issues in GT models. We found that the sensitive features of higher-order nodes disproportionately influence lower-order nodes, resulting in sensitive feature bias. We propose Fairness-aware scalable GT based on Graph Partitioning (FairGP), which partitions the graph to minimize the negative impact of higher-order nodes. By optimizing attention mechanisms, FairGP mitigates the bias introduced by global attention, thereby enhancing fairness. Extensive empirical evaluations on six real-world datasets validate the superior performance of FairGP in achieving fairness compared to state-of-the-art methods. The codes are available at https://github.com/LuoRenqiang/FairGP.