Research map / Graph learning / Graph self-supervised learning
Bayesian Semi-supervised Learning with Graph Gaussian Processes
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 |
|---|---|---|---|
| use GGP rather than GCN | semi-supervised classification · Cora | accuracy: 80.9% vs 81.5% | Hurt |
| use GGP rather than GCN | semi-supervised classification · Citeseer | accuracy: 69.7% vs 70.3% | Hurt |
| use GGP rather than GCN | semi-supervised classification · Pubmed | accuracy: 77.1% vs 79.0% | Hurt |
| add the 500 additional labelled data points to GGP training | GGP · Cora | accuracy: 80.9% -> 84.7% | Helped |
| add the 500 additional labelled data points to GGP training | GGP · Citeseer | accuracy: 69.7% -> 75.6% | Helped |
| add the 500 additional labelled data points to GGP training | GGP · Pubmed | accuracy: 77.1% -> 82.4% | Helped |
| use GGP rather than GCN with SOPT acquisition | active learning · Cora | ALC: 0.706 ± 0.001 -> 0.733 ± 0.001 | Helped |
| use GGP rather than GCN with SOPT acquisition | active learning · Citeseer | ALC: 0.675 ± 0.002 -> 0.678 ± 0.002 | No clear effect |
| use SOPT rather than random acquisition with GGP | GGP active learner · Cora | ALC: 0.575 ± 0.007 -> 0.733 ± 0.001 | Helped |
| use SOPT rather than random acquisition with GGP | GGP active learner · Citeseer | ALC: 0.557 ± 0.008 -> 0.678 ± 0.002 | Helped |
Closest papers by meaning
- Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning (ICLR 2023 · similarity 0.91)
- Uncertainty Aware Graph Gaussian Process for Semi-Supervised Learning (AAAI 2020 · similarity 0.90)
- Multi-Relational Graph Representation Learning with Bayesian Gaussian Process Network (AAAI 2022 · similarity 0.89)
- A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019 · similarity 0.89)
- Graph Convolutional Gaussian Processes (ICML 2019 · similarity 0.89)
- Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations (NeurIPS 2025 · 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.