FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (19) · 16163-16171
DOI: 10.1609/aaai.v40i19.38652 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhenqiang Ye und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Graph neural networks (GNNs) have emerged as the mainstream paradigm for graph representation learning due to their effective message aggregation. However, this advantage also amplifies biases inherent in graph topology, raising fairness concerns. Existing fairness-aware GNNs provide satisfactory performance on fairness metrics such as Statistical Parity and Equal Opportunity while maintaining acceptable accuracy trade-offs. Unfortunately, we observe that this pursuit of fairness metrics neglects the GNN's ability to predict negative labels, which renders their predications with extremely high False Positive Rates (FPRs), resulting in negative effects in high-risk scenarios. To this end, we advocate that classification performance should be carefully calibrated while improving fairness, rather than simply constraining accuracy loss. Furthermore, we propose Fair GNN via Structural Entropy (FairGSE), a novel framework that maximizes two-dimensional structural entropy (2D-SE) to improve fairness without neglecting false positives. Experiments on several real-world datasets show FairGSE reduces FPR by 39% vs. state-of-the-art fairness-aware GNNs, with comparable fairness improvement.
Zitieren
APA
Ye, Z., Lu, J., Gu, T., Hao, F., & Wang, X. (2026). FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates. Proceedings of the AAAI Conference on Artificial Intelligence, 40(19), 16163-16171. https://doi.org/10.1609/aaai.v40i19.38652
Vancouver
Ye Z, Lu J, Gu T, Hao F, Wang X. FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(19):16163-16171. doi:10.1609/aaai.v40i19.38652
BibTeX
@article{Ye2026,
author = {Ye, Zhenqiang and Lu, Jinjie and Gu, Tianlong and Hao, Fengrui and Wang, Xuemin},
title = {FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {19},
pages = {16163--16171},
doi = {10.1609/aaai.v40i19.38652}
}
EUVIMED