Research map / Graph learning / GNN architectures
Learning Fair Graph Representations via Probability of Necessity and Sufficiency
Chuxun Liu, Qingfeng Chen, Debo Cheng, Jiangzhang Gan, Jiuyong Li, Lin Liu
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 necessity and sufficiency (PNS) constraints on top of the discriminator (ablation) | FairSNR · ablation datasets (Figure 4) | F1 and DP trade-off | Improved |
| add the adversarial discriminator (ablation) | FairSNR · ablation datasets (Figure 4) | F1 and DP trade-off | Improved |
| remove necessity/sufficiency constraints (adversarial learning only) (ablation) | FairSNR · ablation datasets (Figure 4) | predictive performance | Hurt |
| set adversarial strength beta to 0.01 (moderate) (ablation) | FairSNR · Credit and Pokec-z | fairness and utility | Improved |
| too small or too large KL weight alpha (ablation) | FairSNR · Credit and Pokec-z | fairness and utility | Hurt |
| FairSNR versus vanilla GCN on small datasets | FairSNR · German | AUC: 73.49 -> 66.17 | Hurt |
| FairSNR versus vanilla GCN on fairness | GCN · German | DP: 33.75 -> 0.64 | Improved |
Closest papers by meaning
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.92)
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.91)
- Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (AAAI 2025 · similarity 0.90)
- Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks (AAAI 2025 · similarity 0.88)
- DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning (ICML 2025 · similarity 0.88)
- FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning (AAAI 2025 · similarity 0.87)
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.
