Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.09210 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915243079237632 |
|---|---|
| author | Liu, Jiaxin Jiang, Xiaoqian Li, Xiang Zhang, Bohan Zhang, Jing |
| author_facet | Liu, Jiaxin Jiang, Xiaoqian Li, Xiang Zhang, Bohan Zhang, Jing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training Liu, Jiaxin Jiang, Xiaoqian Li, Xiang Zhang, Bohan Zhang, Jing Machine Learning Artificial Intelligence Social and Information Networks 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. |
| title | FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Training |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2504.09210 |