{"slug": "subgraph-filtering-for-fair-graph-neural-networks", "title": "Subgraph Filtering for Fair Graph Neural Networks", "summary": "Researchers propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a lightweight, architecture-agnostic framework that mitigates structural bias in GNNs by identifying and filtering bias-prone edges during message passing. Experiments on five benchmark datasets show SF-GNN achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness-accuracy trade-off than recent fairness-aware GNN baselines.", "body_md": "arXiv:2608.26437v1 Announce Type: new\nAbstract: Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features, because graph topology and message passing propagate group-correlated signals under sensitive homophily. Existing fairness-aware GNN methods mainly constrain representations or prediction distributions at a global level, without explicitly controlling the local structural pathways through which biased information propagates during aggregation. We propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a lightweight and architecture-agnostic framework that mitigates structural bias at its source. SF-GNN identifies bias-prone edges by combining sensitive homophily with structural propagation amplifiers, including hub participation and triadic closure. It then incorporates stochastic edge filtering into each message-passing step to selectively downweight or remove these edges while preserving the remaining graph structure. Training further incorporates a statistical-parity regularizer with a warm-up schedule to stabilize optimization. Experiments on five benchmark datasets show that SF-GNN achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness--accuracy trade-off than recent fairness-aware GNN baselines.", "url": "https://wpnews.pro/news/subgraph-filtering-for-fair-graph-neural-networks", "canonical_source": "https://arxiv.org/abs/2608.26437", "published_at": "2026-08-28 04:00:00+00:00", "updated_at": "2026-08-28 04:21:12.520695+00:00", "lang": "en", "topics": ["machine-learning", "ai-ethics"], "entities": ["SF-GNN"], "alternates": {"html": "https://wpnews.pro/news/subgraph-filtering-for-fair-graph-neural-networks", "markdown": "https://wpnews.pro/news/subgraph-filtering-for-fair-graph-neural-networks.md", "text": "https://wpnews.pro/news/subgraph-filtering-for-fair-graph-neural-networks.txt", "jsonld": "https://wpnews.pro/news/subgraph-filtering-for-fair-graph-neural-networks.jsonld"}}