English

FairGC: Fairness-aware Graph Condensation

Machine Learning 2026-03-31 v1

Abstract

Graph condensation (GC) has become a vital strategy for scaling Graph Neural Networks by compressing massive datasets into small, synthetic node sets. While current GC methods effectively maintain predictive accuracy, they are primarily designed for utility and often ignore fairness constraints. Because these techniques are bias-blind, they frequently capture and even amplify demographic disparities found in the original data. This leads to synthetic proxies that are unsuitable for sensitive applications like credit scoring or social recommendations. To solve this problem, we introduce FairGC, a unified framework that embeds fairness directly into the graph distillation process. Our approach consists of three key components. First, a Distribution-Preserving Condensation module synchronizes the joint distributions of labels and sensitive attributes to stop bias from spreading. Second, a Spectral Encoding module uses Laplacian eigen-decomposition to preserve essential global structural patterns. Finally, a Fairness-Enhanced Neural Architecture employs multi-domain fusion and a label-smoothing curriculum to produce equitable predictions. Rigorous evaluations on four real-world datasets, show that FairGC provides a superior balance between accuracy and fairness. Our results confirm that FairGC significantly reduces disparity in Statistical Parity and Equal Opportunity compared to existing state-of-the-art condensation models. The codes are available at https://github.com/LuoRenqiang/FairGC.

Keywords

Cite

@article{arxiv.2603.28321,
  title  = {FairGC: Fairness-aware Graph Condensation},
  author = {Yihan Gao and Chenxi Huang and Wen Shi and Ke Sun and Ziqi Xu and Xikun Zhang and Mingliang Hou and Renqiang Luo},
  journal= {arXiv preprint arXiv:2603.28321},
  year   = {2026}
}

Comments

6 pages, IJCNN 2026 accepted

R2 v1 2026-07-01T11:43:57.301Z