Research map / Graph learning / GNN architectures
On Generalized Degree Fairness in Graph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Modulate each layer's neighborhood aggregation with degree-conditioned debiasing contexts | GCN · Chameleon, Squirrel, EMNLP | ΔDSP: 9.68 ± 1.37 -> 5.85 ± 0.32; 13.37 ± 2.83 -> 9.54 ± 1.02; 44.55 ± 1.90 -> 12.38 ± 3.72 | Helped |
| Modulate each layer's neighborhood aggregation with degree-conditioned debiasing contexts | GCN · Chameleon, Squirrel, EMNLP | ΔDEO: 36.08 ± 2.65 -> 21.60 ± 0.71; 27.00 ± 3.79 -> 16.42 ± 1.38; 34.05 ± 3.56 -> 8.52 ± 2.26 | Helped |
| Modulate each layer's neighborhood aggregation with degree-conditioned debiasing contexts | GCN · Chameleon, Squirrel, EMNLP | accuracy: 62.45 ± 0.21 -> 69.91 ± 0.19; 47.85 ± 1.33 -> 59.21 ± 0.97; 78.92 ± 0.43 -> 79.92 ± 0.77 | Mixed |
| Add node-wise scaling and shifting for debiasing contexts (ablation) | DegreeFair-GCN · three benchmark datasets | accuracy and fairness | Helped |
| Add structural contrast between low- and high-degree groups (ablation) | DegreeFair-GCN · three benchmark datasets | fairness | Helped |
| Add modulation of neighborhood aggregation (ablation) | DegreeFair-GCN · three benchmark datasets | fairness | Helped |
Closest papers by meaning
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.93)
- Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks (AAAI 2025 · similarity 0.90)
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.90)
- Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks (NeurIPS 2024 · similarity 0.90)
- Adversarial Attacks on Fairness of Graph Neural Networks (ICLR 2024 · similarity 0.89)
- Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (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.