Research map / Graph learning / GNN architectures
Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels
Sheng Wan, Yibing Zhan, Liu Liu, Baosheng Yu, Shirui Pan, Chen Gong
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 fixed-graph Poisson learning with attention-based GPN (ablation) | Poisson learning · Cora 1 label/class | accuracy: 46.23 -> 49.26 | Improved |
| replace Poisson learning with GPN (ablation) | Poisson learning · CiteSeer 2 labels/class | accuracy: 40.69 -> 48.24 | Improved |
| add GCN branch plus contrastive loss to GPN (CGPN-GCN) (ablation) | GPN · Cora 1 label/class | accuracy: 49.26 -> 60.64 | Improved |
| add GCN branch plus contrastive loss to GPN (CGPN-GCN) (ablation) | GPN · CiteSeer 2 labels/class | accuracy: 48.24 -> 58.45 | Improved |
| CGPN vs best baseline at 1 label per class | GNN baselines · Cora | accuracy: 56.02 -> 61.17 | Improved |
| CGPN vs best baseline at 1 label per class | GNN baselines · CiteSeer | accuracy: 47.94 -> 52.68 | Improved |
| CGPN vs best baseline at 1 label per class | GNN baselines · PubMed | accuracy: 58.36 -> 61.85 | Improved |
| instantiate CGPN with GAT vs GCN | CGPN · Cora | accuracy: 60.64 -> 61.17 | No clear effect |
| vary lambda1 and lambda2 from 0.1 to 1.5 | CGPN · Cora, CiteSeer | accuracy | No clear effect |
Closest papers by meaning
- Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning (AAAI 2021 · similarity 0.90)
- Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data (ICLR 2024 · similarity 0.90)
- Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle (NeurIPS 2026 · similarity 0.89)
- S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning (ICML 2024 · similarity 0.88)
- Normalize Then Propagate: Efficient Homophilous Regularization for Few-Shot Semi-Supervised Node Classification (AAAI 2025 · similarity 0.87)
- ReGCL: Rethinking Message Passing in Graph Contrastive Learning (AAAI 2024 · similarity 0.87)
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.
