Research map / Graph learning / Graph self-supervised learning
Uncertainty-Constrained Trustworthiness for Graph Learning
Chunhui Zhang, Pengqi Li, Lizhong Ding, Ye Yuan, Peng Yang, Changsheng Li, Guoren 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 |
|---|---|---|---|
| train GNN with DICT objective | GCN · NBA | Delta Acc (%): 26.11 -> 1.73 | Improved |
| train GNN with DICT objective | GCN · German | Delta SP (%): 7.04 -> 1.08 | Improved |
| train GNN with DICT objective | GCN · German | Delta EO (%): 7.47 -> 0.63 | Improved |
| train GNN with DICT objective | GraphSAGE · Bail | Clean Acc (%): 89.13 -> 94.69 | Improved |
| use DICT instead of KCES under Nettack | GCN on Cora · Cora (Nettack) | Attack Acc (%): 78.25 -> 79.32 | Improved |
| use DICT instead of KCES under Metattack | GCN on Cora · Cora (Metattack) | Attack Acc (%): 76.20 -> 78.30 | Improved |
| increase Wasserstein radius r beyond 1.0 (ablation) | DICT · German | robustness and fairness | No clear effect |
| set kappa_A to zero (no penalty on structure perturbations) (ablation) | DICT · German | robustness | Hurt |
| increase kappa_s excessively (ablation) | DICT · German | fairness | Hurt |
| apply DICT to four GNN backbones (GCN, GraphSAGE, GIN, GAT) | DICT · German, Bail, NBA | Delta Acc, Delta SP, Delta EO | Improved |
Closest papers by meaning
- GUIC: Certified Graph Unlearning with Individual Fairness Guarantees (AAAI 2026 · similarity 0.87)
- Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts (NeurIPS 2023 · similarity 0.87)
- On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections (ICLR 2021 · similarity 0.86)
- Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training (AAAI 2025 · similarity 0.84)
- Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory (ICML 2025 · similarity 0.84)
- Robust Graph Condensation via Classification Complexity Mitigation (NeurIPS 2025 · similarity 0.84)
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.
