Hugging Face Trending Papers

Subgraph Filtering for Fair Graph Neural Networks

arXiv Machine Learning
Aug 28

Subgraph Filtering for Fair Graph Neural Networks

Subgraph Filtering for Fair Graph Neural Networks (SF‑GNN) is a lightweight, architecture‑agnostic framework that reduces structural bias in GNNs by identifying and filtering bias‑prone edges during message passing. It combines sensitive homophily with structural propagation amplifiers such as hub participation and triadic closure to detect problematic edges, then applies stochastic edge filtering to downweight or remove them while preserving the rest of the graph. Experiments on five benchmark datasets demonstrate that SF‑GNN consistently improves fairness while maintaining competitive predictive performance, achieving a better fairness–accuracy trade‑off than recent fairness‑aware GNN baselines.

By Haohui Lu, jiyuan Tian, Fangyu Zhou, Shahadat Uddin
arXiv AI
Jun 19

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

arXiv:2606. 20283v1 Announce Type: cross Abstract: Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings.

By Jiaqing Chen, Zidu Yin, Yichao Cai, Yuhang Liu, Zhen Zhang, Dong Gong, Javen Qinfeng Shi