GREAT: GROUP-ACQUIRED BIPARTITE ALIGNMENT FOR GRAPH FAIRNESS ADAPTATION

ICLR 2026 Conference Submission17169 Authors

Keywords: GNN, fairness

Abstract:

Graph neural networks (GNNs) have shown strong performance in graph fairness learning, which aims to ensure that predictions are unbiased with respect to sensitive attributes.
However, existing approaches usually assume that training and test data share the same distribution, which rarely holds in the real world. To tackle this challenge, we propose a novel approach named \underline{D}ual Unbi\underline{a}sed Expa\underline{n}sion with Group-a\underline{c}quired Alignm\underline{e}nt (\method{}) for graph fairness learning under distribution shifts.
The core idea of our \method{} is to synthesize challenging yet unbiased virtual graph data in both graph and hidden spaces, simulating distribution shifts from a data-centric view. Specifically, we introduce the unbiased Mixup in the hidden space, prioritizing minor groups to address the potential imbalance of sensitive attributes. Simultaneously, we conduct fairness-aware adversarial learning in the graph space to focus on challenging samples and improve model robustness. To further bridge the domain gap, we propose a group-acquired alignment objective that prioritizes negative pair groups with identical sensitive labels. Additionally, a representation disentanglement objective is adopted to decorrelate sensitive attributes and target representations for enhanced fairness.
Extensive experiments demonstrate the superior effectiveness of the proposed \method{}.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 17169