# Subgraph Filtering for Fair Graph Neural Networks

arXiv: https://arxiv.org/abs/2608.26437 · HTML: https://mlsanity.com/paper/2608.26437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Representing Long-Range Context for Graph Neural Networks with Global Attention](https://mlsanity.com/paper/2201.08821/) (2022)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [FairGT: A Fairness-aware Graph Transformer](https://mlsanity.com/paper/2404.17169/) (2024)
- [FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization](https://mlsanity.com/paper/2403.12474/) (2024)
- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)
- [Relational Graph Modeling for Credit Default Prediction: Heterogeneous GNNs and Hybrid Ensemble Learning](https://mlsanity.com/paper/2601.14633/) (2026)

## Abstract (arXiv)

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.