FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning

TL;DR

FairGP introduces a scalable graph transformer that uses graph partitioning and attention optimization to improve fairness and reduce computational demands on large-scale graphs.

Contribution

It proposes a novel Fairness-aware scalable Graph Transformer (FairGP) that leverages graph partitioning and optimized attention to enhance fairness and efficiency.

Findings

FairGP outperforms state-of-the-art methods in fairness on six datasets.

Graph partitioning reduces bias caused by higher-order nodes.

FairGP decreases computational complexity compared to traditional GTs.

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.