Research map / Graph learning / GNN architectures
Fair Graph Distillation
Qizhang Feng, Zhimeng Jiang, Ruiquan Li, Yicheng Wang, Na Zou, Jiang Bian, Xia Hu
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 FGD coherence-bias debiasing to graph distillation | GCN on distilled graph · Pokec-z | ΔDP: 2.84±1.1% -> 1.75±1.1% | Improved |
| add FGD debiasing | GCN on distilled graph · Pokec-n | ΔDP: 4.02±0.6% -> 0.66±0.5% | Improved |
| add FGD debiasing | GCN on distilled graph · German | ΔDP: 5.38±3.3% -> 1.93±0.1% | Improved |
| add FGD debiasing | GCN on distilled graph · Credit | ΔDP: 12.04±5.4% -> 4.94±4.8% | Improved |
| add FGD debiasing | GCN on distilled graph · Recidivism | ΔDP: 2.68±1.0% -> 0.54±0.3% | Improved |
| add FGD debiasing | GCN on distilled graph · Pokec-n | accuracy: 50.10±2.7% -> 54.80±1.5% | Improved |
| add FGD debiasing | GCN on distilled graph · German | accuracy: 72.83±0.8% -> 70.50±0.1% | Hurt |
| add FGD debiasing | GCN on distilled graph · Recidivism | accuracy: 70.89±1.8% -> 70.09±2.6% | No clear effect |
| train on distilled graph instead of real graph | GCN · Recidivism | accuracy: 94.45±0.0% -> 70.89±1.8% | Hurt |
| coherence bias regularization | distilled graph · Pokec-z | coherence bias: 0.009468 -> 0.002123 | Improved |
| coherence bias regularization | distilled graph · Recidivism | coherence bias: 0.000098 -> 0.000038 | Improved |
| increase alpha regularization weight (ablation) | FGD · Recidivism | AUC and ΔDP: AUC 74.75 -> 65.35, ΔDP 0.84 -> 0.00 | Mixed |
Closest papers by meaning
- Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks (AAAI 2025 · similarity 0.89)
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.89)
- Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (AAAI 2025 · similarity 0.89)
- Adversarial Attacks on Fairness of Graph Neural Networks (ICLR 2024 · similarity 0.88)
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.87)
- Deceptive Fairness Attacks on Graphs via Meta Learning (ICLR 2024 · 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.
