Subgraph Filtering for Fair Graph Neural Networks

• URL: http://arxiv.org/abs/2608.26437v1
• Date: Wed, 26 Aug 2026 22:40:31 GMT
• Title: Subgraph Filtering for Fair Graph Neural Networks
• Abstract summary: Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features.<n>We propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN)<n>SF-GNN identifies bias-prone edges by combining sensitive homophily with structural propagation amplifiers.<n>It then incorporates edge filtering into each message-passing step to selectively downweight or remove these edges while preserving the remaining graph structure.
• Score: 4.075849063907074
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• FnRGNN: Distribution-aware Fairness in Graph Neural Network [4.013463458124476]
  Graph Neural Networks (GNNs) excel at learning from structured data, yet fairness in regression tasks remains underexplored.<n>We propose FnRGNN, a fairness-aware in-processing framework for GNN-based node regression.
  arXiv  Detail & Related papers  (2025-10-22T05:29:43Z)
• Improving Fairness in Graph Neural Networks via Counterfactual Debiasing [4.984092292992338]
  Graph Neural Networks (GNNs) have been successful in modeling graph-structured data.<n>GNNs can exhibit bias in predictions based on attributes like race and gender.<n>We present a novel approach utilizing counterfactual data augmentation for bias mitigation.
  arXiv  Detail & Related papers  (2025-08-20T12:59:05Z)
• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions [64.17845687013434]
  We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
  arXiv  Detail & Related papers  (2025-07-19T04:46:53Z)
• Directed Homophily-Aware Graph Neural Network [7.539052660225002]
  We propose Directed Homophily-aware Graph Neural Network (DHGNN), a novel framework that incorporates homophily-aware and direction-sensitive components.<n>DHGNN employs a resettable gating mechanism to adaptively modulate message contributions based on homophily levels and informativeness.<n>Our analysis shows that the gating mechanism captures directional homophily gaps and fluctuating homophily across layers, providing deeper insights into message-passing behavior on complex graph structures.
  arXiv  Detail & Related papers  (2025-05-28T13:41:04Z)
• Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation [23.79865440689265]
  Graph Neural Networks (GNNs) have recently become the predominant tools for studying graph data.<n>Despite state-of-the-art performance on graph classification tasks, GNNs are overwhelmingly trained in a single domain under supervision.<n>We propose the Label-Propagation Graph Neural Network (LP-TGNN) framework to bridge the gap between graph data and traditional domain adaptation methods.
  arXiv  Detail & Related papers  (2025-02-12T15:36:38Z)
• Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
  We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs) 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. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
  arXiv  Detail & Related papers  (2023-12-19T18:00:15Z)
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs [51.33152272781324]
  Graph Neural Networks (GNNs) are proposed without considering the distribution shifts between training and testing graphs. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. We propose a general causal representation framework, called StableGNN, to eliminate the impact of spurious correlations.
  arXiv  Detail & Related papers  (2021-11-20T18:57:18Z)
• Training Stable Graph Neural Networks Through Constrained Learning [116.03137405192356]
  Graph Neural Networks (GNNs) rely on graph convolutions to learn features from network data. GNNs are stable to different types of perturbations of the underlying graph, a property that they inherit from graph filters. We propose a novel constrained learning approach by imposing a constraint on the stability condition of the GNN within a perturbation of choice.
  arXiv  Detail & Related papers  (2021-10-07T15:54:42Z)
• Bayesian Graph Neural Networks with Adaptive Connection Sampling [62.51689735630133]
  We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs.
  arXiv  Detail & Related papers  (2020-06-07T07:06:35Z)
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks [183.97265247061847]
  We leverage graph signal processing to characterize the representation space of graph neural networks (GNNs) We discuss the role of graph convolutional filters in GNNs and show that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology. We also study the use of GNNs in recommender systems and learning decentralized controllers for robot swarms.
  arXiv  Detail & Related papers  (2020-03-08T13:02:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.