EUVIMEDEUVIMED entdecken
Crossref

Chasing Fairness in Graphs: A GNN Architecture Perspective

Zhimeng Jiang, Xiaotian Han, Chao Fan, Zirui Liu, Na Zou, Ali Mostafavi, Xia Hu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (19) · 21214-21222

DOI: 10.1609/aaai.v38i19.30115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zhimeng Jiang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose Fair Message Passing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP explicitly renders sensitive attribute usage in forward propagation for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available at https://github.com/zhimengj0326/FMP.

Zitieren

APA

Jiang, Z., Han, X., Fan, C., Liu, Z., Zou, N., Mostafavi, A., & Hu, X. (2024). Chasing Fairness in Graphs: A GNN Architecture Perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 38(19), 21214-21222. https://doi.org/10.1609/aaai.v38i19.30115

Vancouver

Jiang Z, Han X, Fan C, Liu Z, Zou N, Mostafavi A, et al. Chasing Fairness in Graphs: A GNN Architecture Perspective. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(19):21214-21222. doi:10.1609/aaai.v38i19.30115

BibTeX
@article{Jiang2024,
  author = {Jiang, Zhimeng and Han, Xiaotian and Fan, Chao and Liu, Zirui and Zou, Na and Mostafavi, Ali and Hu, Xia},
  title = {Chasing Fairness in Graphs: A GNN Architecture Perspective},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {19},
  pages = {21214--21222},
  doi = {10.1609/aaai.v38i19.30115}
}
Kostenlos starten →