Research map / Graph learning / GNN architectures
FairGSE: Fairness-Aware Graph Neural Network Without High False Positive Rates
Zhenqiang Ye, Jinjie Lu, Tianlong Gu, Fengrui Hao, Xuemin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add 2D structural entropy maximization with contrastive learning to a GCN | Vanilla GCN · Credit | FPR (%): 45.96 -> 41.45 | Improved |
| add 2D structural entropy maximization with contrastive learning to a GCN | Vanilla GCN · Credit | ΔSP (%): 14.63 -> 5.09 | Improved |
| FairGSE versus FairSIN, which reaches near-zero ΔSP via a false-positive shortcut | FairSIN · Credit | FPR (%): 99.76 -> 41.45 | Improved |
| FairGSE versus FairSIN on group fairness | FairSIN · Credit | ΔSP (%): 0.52 -> 5.09 | Hurt |
| FairGSE versus second-best method on Pokec n | FairGP · Pokec n | FPR (%): 18.98 -> 18.46 | Improved |
| add graph structure learner (2D-SE maximization) on top of contrastive learning (ablation) | FairGSE · Credit | FPR | Improved |
| add contrastive learning to 2D-SE structure learning (ablation) | FairGSE · Credit, Pokec n, Pokec z | AUC/FPR/fairness | Improved |
| add structure bootstrapping mechanism (ablation) | FairGSE · Credit | fairness (ΔSP, ΔEO) | Improved |
| add structure bootstrapping mechanism (ablation) | FairGSE · Pokec n, Pokec z | overall performance | No clear effect |
| increase contrastive weight lambda1 beyond 0.5 (ablation) | FairGSE · Credit | FPR | Mixed |
| use smaller 2D-SE weight lambda2 (ablation) | FairGSE · Credit | fairness-FPR trade-off | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FairGP — FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning (AAAI 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.91)
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.91)
- Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (AAAI 2025 · similarity 0.90)
- Adversarial Attacks on Fairness of Graph Neural Networks (ICLR 2024 · similarity 0.89)
- FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning (AAAI 2025 · similarity 0.89)
- Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
