EUVIMEDEUVIMED entdecken
Crossref

Learning Fair Graph Representations via Probability of Necessity and Sufficiency

Chuxun Liu, Qingfeng Chen, Debo Cheng, Jiangzhang Gan, Jiuyong Li, Lin Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23667-23675

DOI: 10.1609/aaai.v40i28.39540 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chuxun Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Networks (GNNs) excel at modeling graph data but often amplify biases tied to sensitive attributes like gender and race. Existing causality-based methods use isolated interventions on graph topology or features but struggle to produce representations that balance predictive power with fairness. This leads to two issues: (1) weak predictive power, where representations miss critical task-relevant features, and (2) bias amplification, where representations encode sensitive attributes, causing unfair outcomes. To address these issues, we introduce the Probability of Necessity and Sufficiency (PNS), where necessity ensures representations capture only essential features for predictions, and sufficiency guarantees these features are adequate without relying on sensitive attributes. We propose FairSNR, a fairness-aware graph representation learning framework that introduces constraints based on the PNS. This leverages PNS to guide the learning of fair representations from graph data. In particular, FairSNR employs an encoder to learn node representations with high PNS for downstream tasks. To compute and optimize PNS, FairSNR introduces an intervenor to generate the most challenging counterfactual interventions on the representations, thereby enhancing the model’s causal stability even under worst-case scenarios. Further, a discriminator is trained to detect and mitigate sensitive information leakage in the learned representations, effectively disentangling sensitive biases from task-relevant features. Experiments on real-world graph datasets demonstrate that FairSNR outperforms existing state-of-the-art (SOTA) methods in both fairness and utility.

Zitieren

APA

Liu, C., Chen, Q., Cheng, D., Gan, J., Li, J., & Liu, L. (2026). Learning Fair Graph Representations via Probability of Necessity and Sufficiency. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23667-23675. https://doi.org/10.1609/aaai.v40i28.39540

Vancouver

Liu C, Chen Q, Cheng D, Gan J, Li J, Liu L. Learning Fair Graph Representations via Probability of Necessity and Sufficiency. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23667-23675. doi:10.1609/aaai.v40i28.39540

BibTeX
@article{Liu2026,
  author = {Liu, Chuxun and Chen, Qingfeng and Cheng, Debo and Gan, Jiangzhang and Li, Jiuyong and Liu, Lin},
  title = {Learning Fair Graph Representations via Probability of Necessity and Sufficiency},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {28},
  pages = {23667--23675},
  doi = {10.1609/aaai.v40i28.39540}
}
Kostenlos starten →