FairGC: Fairness-aware Graph Condensation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911553528266752 |
|---|---|
| author | Gao, Yihan Huang, Chenxi Shi, Wen Sun, Ke Xu, Ziqi Zhang, Xikun Hou, Mingliang Luo, Renqiang |
| author_facet | Gao, Yihan Huang, Chenxi Shi, Wen Sun, Ke Xu, Ziqi Zhang, Xikun Hou, Mingliang Luo, Renqiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28321 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FairGC: Fairness-aware Graph Condensation Gao, Yihan Huang, Chenxi Shi, Wen Sun, Ke Xu, Ziqi Zhang, Xikun Hou, Mingliang Luo, Renqiang Machine Learning 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. |
| title | FairGC: Fairness-aware Graph Condensation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.28321 |