Research map / Graph learning / Graph self-supervised learning
Provable Training for Graph Contrastive Learning
Yue Yu, Xiao Wang, Mengmei Zhang, Nian Liu, Chuan Shi
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 POT regularization to GRACE | GRACE · CiteSeer | Mi-F1: 66.8 ± 1.0 -> 68.7 ± 0.6 | Improved |
| Add POT regularization to GCA | GCA · CiteSeer | Mi-F1: 65.0 ± 0.7 -> 69.0 ± 0.8 | Improved |
| Add POT regularization to ProGCL | ProGCL · Cora | Mi-F1: 77.9 ± 1.4 -> 79.9 ± 1.0 | Improved |
| Add POT regularization to COSTA | COSTA · Flickr | Mi-F1: 52.6 ± 1.2 -> 53.8 ± 1.2 | Improved |
| Add POT to GRACE with centrality-based edge dropping | GRACE · Flickr, degree-centrality augmentation | F1Mi: 47.4 ± 0.8 -> 50.3 ± 0.3 | Improved |
| Tune the POT weighting parameter κ | GCL with POT · BlogCatalog | Micro-F1 | Mixed |
Closest papers by meaning
- Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling (AAAI 2025 · similarity 0.94)
- ReGCL: Rethinking Message Passing in Graph Contrastive Learning (AAAI 2024 · similarity 0.92)
- Perfect Alignment May be Poisonous to Graph Contrastive Learning (ICML 2024 · similarity 0.91)
- Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning (AAAI 2024 · similarity 0.91)
- S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning (ICML 2024 · similarity 0.91)
- Beyond Homophily: Graph Contrastive Learning with Macro-Micro Message Passing (AAAI 2025 · similarity 0.91)
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.
