Research map / Graph learning / Graph self-supervised learning
Graph Contrastive Learning with Balanced Hard Negatives and Fine-grained Semantic-aware Positives
Hongshan Pu, Haoxu Zhang, Ye Liu, Hongmin Cai
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 the BHN balanced hard negative module (ablation) | BalanceGCL · ENZYMES | accuracy: 56.79 -> 60.29 | Improved |
| add the BHN balanced hard negative module (ablation) | BalanceGCL · Synthie | accuracy: 74.35 -> 78.75 | Improved |
| add class-balance loss Lc instead of CGC KL loss (ablation) | BalanceGCL · ENZYMES | accuracy: 57.34 -> 60.29 | Improved |
| add class-balance loss Lc instead of CGC KL loss (ablation) | BalanceGCL · Synthie | accuracy: 76.20 -> 78.75 | Improved |
| add the FSP fine-grained positive module (ablation) | BalanceGCL · ENZYMES | accuracy: 56.65 -> 60.29 | Improved |
| add the FSP fine-grained positive module (ablation) | BalanceGCL · COLORS-3 | accuracy: 75.40 -> 80.18 | Improved |
| add positively contributing region perturbation (ablation) | BalanceGCL · COLORS-3 | accuracy: 77.31 -> 80.18 | Improved |
| add negatively contributing region suppression (ablation) | BalanceGCL · Synthie | accuracy: 77.50 -> 78.75 | Improved |
| add unimportant region random perturbation (ablation) | BalanceGCL · ENZYMES | accuracy: 59.32 -> 60.29 | Improved |
| use both attribute and edge perturbation instead of attribute only (ablation) | BalanceGCL-attr · ENZYMES | accuracy: 59.68 -> 60.29 | Improved |
| use both attribute and edge perturbation instead of edge only (ablation) | BalanceGCL-edge · ENZYMES | accuracy: 58.37 -> 60.29 | Improved |
| use BalanceGCL instead of DRGCL | DRGCL · COLORS-3 | accuracy: 78.90 -> 80.18 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InfoGraph — InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (ICLR 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
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)
- Improving Graph Contrastive Learning via Adaptive Positive Sampling (CVPR 2024 · similarity 0.90)
- ReGCL: Rethinking Message Passing in Graph Contrastive Learning (AAAI 2024 · similarity 0.90)
- Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning (AAAI 2024 · similarity 0.89)
- S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning (ICML 2024 · similarity 0.89)
- Perfect Alignment May be Poisonous to Graph Contrastive Learning (ICML 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.
