Research map / Graph learning / Graph self-supervised learning
Uncertainty Aware Semi-Supervised Learning on Graph Data
Xujiang Zhao, Feng Chen, Shu Hu, Jin-Hee Cho
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 GKDE prior (S-BGCN-T-K vs S-BGCN-T) (ablation) | S-BGCN-T · Amazon Photo OOD detection | AUROC (vacuity): 64.0 -> 93.4 | Improved |
| add GKDE prior (ablation) | S-BGCN-T · Cora misclassification detection | AUROC (dissonance): 82.5 -> 82.4 | No clear effect |
| add GKDE prior (ablation) | S-BGCN-T · Cora node classification | accuracy: 82.2 -> 82.0 | No clear effect |
| add teacher network (ablation) | S-BGCN · Cora node classification | accuracy: 81.2 -> 82.2 | Improved |
| add Bayesian dropout framework to S-GCN (ablation) | S-GCN · Cora node classification | accuracy: 81.5 -> 81.2 | Hurt |
| add teacher network (ablation) | S-BGCN · Cora misclassification detection | AUROC (dissonance): 81.4 -> 82.5 | Improved |
| use dissonance instead of entropy as uncertainty measure | S-BGCN-T-K · Cora misclassification detection | AUROC: 77.7 -> 82.4 | Improved |
| use vacuity instead of epistemic uncertainty | S-BGCN-T-K · Amazon Photo OOD detection | AUROC: 32.2 -> 93.4 | Improved |
| use S-BGCN-T-K vacuity instead of EDL-GCN vacuity | OOD detection · Amazon Computer OOD detection | AUROC (vacuity): 53.2 -> 82.3 | Improved |
Closest papers by meaning
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks (ICLR 2024 · similarity 0.90)
- A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion (NeurIPS 2026 · similarity 0.89)
- Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory (ICML 2025 · similarity 0.89)
- Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification (ICML 2024 · similarity 0.88)
- Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations (NeurIPS 2025 · similarity 0.88)
- Random-Set Graph Neural Networks (NeurIPS 2026 · similarity 0.88)
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.
