FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning

2024-12-14

AI Summary

Existing graph Transformers (GTs) suffer from prohibitive computational overhead and poor subgroup fairness. This paper proposes the first scalable and fair GT framework based on graph partitioning. First, we theoretically characterize the bias propagation mechanism—where higher-order sensitive features induce bias in lower-order node representations. Then, we jointly design graph partitioning and fairness-aware attention to simultaneously achieve structural compression and bias mitigation. Evaluated on six real-world datasets, our method significantly outperforms state-of-the-art approaches: fairness metrics (Statistical Parity Difference and Equalized Odds Difference) improve by 37% on average; inference memory consumption decreases by 52%; and training speed increases by 2.1×. To the best of our knowledge, this is the first GT framework that concurrently ensures strong group fairness and computational scalability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Graph Transformers
• Resource Consumption
• Label Fairness

Innovation

• FairGP
• Attention Mechanism Improvement
• Graph Transformer Fairness