Research map / Graph learning / Graph self-supervised learning
Uncertainty Aware Graph Gaussian Process for Semi-Supervised Learning
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 |
|---|---|---|---|
| add uncertainty-aware label smooth regularization and Euclidean aggregation to GGP (UaGGP vs GGP) | GGP · Cora | accuracy: 80.9% -> 82.7% | Helped |
| UaGGP vs GGP | GGP · Citeseer | accuracy: 69.7% -> 70.7% | Helped |
| UaGGP vs GGP | GGP · Pubmed | accuracy: 77.1% -> 76.7% | Hurt |
| add Euclidean-space feature aggregation to Hilbert-only UaGGP (ablation) | UaGGP · Cora | accuracy: 82.3% -> 82.7% | Helped |
| add Euclidean-space feature aggregation to Hilbert-only UaGGP (ablation) | UaGGP · Citeseer | accuracy: 70.1% -> 70.7% | Helped |
| add Euclidean-space feature aggregation to Hilbert-only UaGGP (ablation) | UaGGP · Pubmed (100 labels) | accuracy: 76.5% -> 77.5% | Helped |
| add Hilbert-space aggregation to Euclidean-only GGP (ablation) | GGP · Cora | accuracy: 81.6% -> 82.8% | Helped |
| add label smooth regularization when labels are very scarce | UaGGP · Citeseer (50 labels) | accuracy: 45.8 ± 2.26 -> 32.8 ± 1.61 | Hurt |
| UaGGP vs GGP with 50 labels | GGP · Cora (50 labels) | accuracy: 47.2 ± 0.44 -> 51.0 ± 0.34 | Helped |
| too large regularization weight lambda (ablation) | UaGGP · Cora/Pubmed | accuracy | Hurt |
Closest papers by meaning
- Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations (NeurIPS 2025 · similarity 0.88)
- Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data (AAAI 2024 · similarity 0.87)
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks (ICLR 2024 · similarity 0.85)
- Uncertainty for Active Learning on Graphs (ICML 2024 · similarity 0.85)
- Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory (ICML 2025 · similarity 0.85)
- Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification (ICML 2024 · 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.