Research map / Graph learning / GNN architectures
Fair Graph Machine Learning under Adversarial Missingness Processes
Debolina Halder Lina, Arlei Silva
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 |
|---|---|---|---|
| use BFtS worst-case 3-player imputation instead of RNF when no sensitive attributes are available | fair GNN node classification · BAIL, no sensitive info | ΔDP (%): 11.65 -> 8.01 | Improved |
| BFtS vs RNF accuracy on NBA and Pokec-n without sensitive info | BFtS · NBA and Pokec-n, no sensitive info | F1 (%): NBA 70.2 -> 69.8; Pokec-n 72.2 -> 69.6 | Mixed |
| select low-degree nodes to have missing sensitive values (degree heuristic) | independent GCN imputation · multiple graph datasets | bias underestimation | Hurt |
| targeted missingness heuristic vs degree heuristic (ablation) | independent imputation · multiple graph datasets | bias discrepancy | No clear effect |
| BFtS worst-case imputation under adversarial missingness | BFtS · imputed vs true bias | bias underestimation | Improved |
| BFtS with higher assortativity vs low assortativity on synthetic graph | baselines FairGNN and Debias · Simulation dataset | label learning | Hurt |
| BFtS vs Debias on running time | BFtS · six datasets | running time: German 21.74 (Debias) vs 28.91 (BFtS) | Hurt |
| vary alpha vs beta hyperparameters (ablation) | BFtS · sensitivity analysis | fairness-accuracy | Mixed |
Closest papers by meaning
- FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization (AAAI 2024 · similarity 0.90)
- Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.90)
- Adversarial Attacks on Fairness of Graph Neural Networks (ICLR 2024 · similarity 0.89)
- Deceptive Fairness Attacks on Graphs via Meta Learning (ICLR 2024 · similarity 0.88)
- Adversarial Fairness Network (AAAI 2024 · similarity 0.87)
- Stable Fair Graph Representation Learning with Lipschitz Constraint (ICML 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.
