FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training
This addresses fairness issues in GNNs for applications like social networks or recommendation systems, but it is incremental as it builds on existing fairness methods with new techniques.
The paper tackles the problem of degree bias in graph neural networks (GNNs), which leads to unequal prediction performance across nodes with different degrees, and proposes FairACE, a framework that integrates asymmetric contrastive learning and adversarial training to improve fairness, achieving significant gains in fairness metrics while maintaining competitive accuracy.
Fairness has been a significant challenge in graph neural networks (GNNs) since degree biases often result in un-equal prediction performance among nodes with varying degrees. Existing GNN models focus on prediction accuracy, frequently overlooking fairness across different degree groups. To addressthis issue, we propose a novel GNN framework, namely Fairness- Aware Asymmetric Contrastive Ensemble (FairACE), which inte-grates asymmetric contrastive learning with adversarial training to improve degree fairness. FairACE captures one-hop local neighborhood information and two-hop monophily similarity to create fairer node representations and employs a degree fairness regulator to balance performance between high-degree and low-degree nodes. During model training, a novel group-balanced fairness loss is proposed to minimize classification disparities across degree groups. In addition, we also propose a novel fairness metric, the Accuracy Distribution Gap (ADG), which can quantitatively assess and ensure equitable performance across different degree-based node groups. Experimental results on both synthetic and real-world datasets demonstrate that FairACE significantly improves degree fairness metrics while maintaining competitive accuracy in comparison to the state-of-the-art GNN models.