Subgraph Filtering for Fair Graph Neural Networks
Summary
This paper proposes Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a framework that mitigates structural bias in GNNs by filtering edges to improve fairness-accuracy trade-offs.
View Cached Full Text
Cached at: 08/28/26, 09:39 AM
# Subgraph Filtering for Fair Graph Neural Networks Source: [https://arxiv.org/abs/2608.26437](https://arxiv.org/abs/2608.26437) [View PDF](https://arxiv.org/pdf/2608.26437)[HTML \(experimental\)](https://arxiv.org/html/2608.26437v1) > Abstract: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\. ## Submission history From: Haohui Lu \[[view email](https://arxiv.org/show-email/87f59061/2608.26437)\] **\[v1\]**Wed, 26 Aug 2026 22:40:31 UTC \(148 KB\)
Similar Articles
Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation
This paper presents a comprehensive benchmark for evaluating adversarial attacks and defenses in Graph Neural Networks, highlighting the need for standardized and fair experimental protocols.
Convex--Concave Quadratic Spectral Filtering for Graph Neural Networks
Proposes DCQ-GNN, a spectral GNN that uses a compact bank of adaptive convex-concave quadratic filters to improve spectral selectivity without high-order polynomials, achieving competitive results on both homophilic and heterophilic graphs.
Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
This paper proposes CE-FedGNN, a federated graph neural network framework that achieves communication efficiency and privacy preservation by infrequently exchanging aggregated node representations with metric differential privacy guarantees, and demonstrates strong performance on benchmarks.
Schreier-Coset Graph Rewiring
Introduces Schreier-Coset Graph Rewiring, a group-theoretic method to rewire graphs for GNNs, mitigating over-squashing by improving spectral gap and effective resistance. Empirical results show significant reduction in effective resistance across learning tasks.
Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement
Proposes ACE, a plug-and-play method that adaptively enhances coarsening-based GNN training on heterophilic graphs by reconstructing node features and applying anisotropic regularization, achieving consistent gains on heterophilic benchmarks with minimal overhead.