Fair Graph Learning with Limited Sensitive Attribute Information
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (46) · 39423-39431
DOI: 10.1609/aaai.v40i46.41292 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zichong Wang und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Graph neural networks (GNNs) excel at modeling graph-structured data but often inherit and amplify biases, leading to substantial efforts in developing fair GNNs. However, most existing approaches assume full access to sensitive attribute information, which is often impractical in real-world scenarios due to privacy concerns or risks of discrimination. To address this limitation, this paper focuses on graph fairness with limited sensitive attribute information, ensuring applicability to real-world contexts where current methods fall short. Specifically, we introduce an innovative fairness optimization strategy, propose a novel framework named FGLISA, and provide a theoretical perspective linking limited sensitive attribute information access to fairness objectives, thus enabling fair graph learning in real-world applications with limited sensitive attribute information. Experiments on diverse real-world datasets and tasks validate the effectiveness of our approach in achieving both fairness and predictive performance.
Zitieren
APA
Wang, Z., Yang, J., Zhuang, J., Jiang, P., Chen, M., Hu, Y., & Zhang, W. (2026). Fair Graph Learning with Limited Sensitive Attribute Information. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39423-39431. https://doi.org/10.1609/aaai.v40i46.41292
Vancouver
Wang Z, Yang J, Zhuang J, Jiang P, Chen M, Hu Y, et al. Fair Graph Learning with Limited Sensitive Attribute Information. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(46):39423-39431. doi:10.1609/aaai.v40i46.41292
BibTeX
@article{Wang2026,
author = {Wang, Zichong and Yang, Jie and Zhuang, Jun and Jiang, Puqing and Chen, Mingzhe and Hu, Ye and Zhang, Wenbin},
title = {Fair Graph Learning with Limited Sensitive Attribute Information},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {46},
pages = {39423--39431},
doi = {10.1609/aaai.v40i46.41292}
}
EUVIMED