Research map / Graph learning / GNN architectures
Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
Kexin Huang, Ying Jin, Emmanuel Candes, Jure Leskovec
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 |
|---|---|---|---|
| replace inefficiency loss with standard prediction loss in correction step (ablation) | CF-GNN · Cora (GCN) | prediction set size: 1.76 -> 2.42 when removed | Improved |
| replace inefficiency loss with standard prediction loss (ablation) | CF-GNN · Anaheim (GCN) | interval length: 2.17 -> 2.23 when removed | Improved |
| use GNN instead of MLP as correction model (ablation) | CF-GNN · Cora (GCN) | prediction set size: 2.35 -> 1.76 | Improved |
| use GNN instead of MLP as correction model (ablation) | CF-GNN · Anaheim (GCN) | interval length: 2.32 -> 2.17 | Improved |
| add topology-aware correction and inefficiency loss to plain CP | CF-GNN · Cora (GCN) | prediction set size: 3.80 -> 1.76 | Improved |
| add CF-GNN correction to plain CP for regression | CF-GNN · Election / Chicago (GCN) | interval length: 0.90 -> 0.90; 2.05 -> 2.04 | No clear effect |
| CF-GNN vs plain CP regression on Anaheim | CF-GNN · Anaheim (GCN) | interval length: 2.89 -> 2.17 | Improved |
| CF-GNN vs plain CP on conditional coverage over PageRank slices (classification) | CF-GNN · Cora | worst-slice coverage: 0.78 -> 0.94 | Improved |
| CF-GNN vs plain CP conditional coverage for regression | CF-GNN · Twitch | worst-slice coverage: 0.94 -> 0.94 (PageRank) | No clear effect |
Closest papers by meaning
- Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training (AAAI 2025 · similarity 0.93)
- GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs (NeurIPS 2026 · similarity 0.90)
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks (ICLR 2024 · similarity 0.90)
- Valid Conformal Prediction for Dynamic GNNs (ICLR 2025 · similarity 0.89)
- A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion (NeurIPS 2026 · similarity 0.89)
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · 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.
