FairGT: A Fairness-aware Graph Transformer
This addresses fairness issues in graph learning for sensitive subgroups, representing an incremental improvement by adapting fairness techniques to Graph Transformers.
The paper tackles the problem of fairness in Graph Transformers, which often produce biased outcomes, by proposing FairGT, a fairness-aware model that incorporates structural feature selection and multi-hop node feature integration. Empirical results on five real-world datasets show FairGT outperforms existing methods in fairness metrics.
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.