FairGT: A Fairness-aware Graph Transformer

TL;DR

FairGT is a novel graph transformer model designed to improve fairness in graph learning by incorporating structural feature selection and multi-hop node feature integration, effectively reducing bias against sensitive subgroups.

Contribution

We introduce FairGT, a fairness-aware graph transformer that explicitly mitigates bias through innovative structural encoding and feature integration techniques, with theoretical and empirical validation.

Findings

Outperforms existing methods in fairness metrics across five datasets.

Effectively reduces bias against sensitive subgroups.

Theoretically proven effectiveness of structural encodings.

Abstract

The design of Graph Transformers (GTs) generally neglects considerations for fairness, resulting in biased outcomes against certain sensitive subgroups. Since GTs encode graph information without relying on message-passing mechanisms, conventional fairness-aware graph learning methods cannot be directly applicable to address these issues. To tackle this challenge, we propose FairGT, a Fairness-aware Graph Transformer explicitly crafted to mitigate fairness concerns inherent in GTs. FairGT incorporates a meticulous structural feature selection strategy and a multi-hop node feature integration method, ensuring independence of sensitive features and bolstering fairness considerations. These fairness-aware graph information encodings seamlessly integrate into the Transformer framework for downstream tasks. We also prove that the proposed fair structural topology encoding with adjacency matrix eigenvector selection and multi-hop integration are theoretically effective. Empirical evaluations conducted across five real-world datasets demonstrate FairGT's superiority in fairness metrics over existing graph transformers, graph neural networks, and state-of-the-art fairness-aware graph learning approaches.