Research map / Graph learning / Graph self-supervised learning
MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning
Xumeng Gong, Cheng Yang, 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 asymmetric strategy to the base model (ablation) | Base Model · six node-classification benchmarks | average accuracy: 85.42 | Improved |
| add random strategy to the base model (ablation) | Base Model · six node-classification benchmarks | average accuracy: 85.19 | Improved |
| add shuffling strategy to the base model (ablation) | Base Model · six node-classification benchmarks | average accuracy: 85.02 | Improved |
| add asymmetric strategy (ablation) | MA-GCL · six node-classification benchmarks | average accuracy: 85.49 -> 86.20 | Improved |
| add random strategy (ablation) | MA-GCL · six node-classification benchmarks | average accuracy: 85.83 -> 86.20 | Improved |
| add shuffling strategy (ablation) | MA-GCL · six node-classification benchmarks | average accuracy: 85.73 -> 86.20 | Improved |
| use MA-GCL rather than CCA-SSG | node classification · Cora | accuracy: 83.9 ± 0.4 -> 83.3 ± 0.4 | Hurt |
| use MA-GCL rather than CCA-SSG | node classification · CiteSeer | accuracy: 73.1 ± 0.3 -> 73.6 ± 0.1 | Improved |
| use MA-GCL rather than CCA-SSG | node classification · PubMed | accuracy: 81.3 ± 0.4 -> 83.5 ± 0.4 | Improved |
| use MA-GCL rather than SimGRACE | node classification · Coauthor-CS | accuracy: 93.45 ± 0.4 -> 94.19 ± 0.1 | Improved |
| use MA-GCL rather than CCA-SSG | node classification · Amazon-Computers | accuracy: 88.42 ± 0.3 -> 88.83 ± 0.3 | Improved |
| use MA-GCL rather than BGRL | node classification · Amazon-Photo | accuracy: 92.57 ± 0.3 -> 93.80 ± 0.1 | Improved |
Later papers that compared with this method
1 later accepted paper reports MA-GCL as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- ASWT-SGNN: Adaptive Spectral Wavelet Transform-Based Self-Supervised Graph Neural Network (AAAI 2024 · better on 0 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
- Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model (AAAI 2025 · similarity 0.91)
- Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling (AAAI 2025 · similarity 0.91)
- Perfect Alignment May be Poisonous to Graph Contrastive Learning (ICML 2024 · similarity 0.90)
- ReGCL: Rethinking Message Passing in Graph Contrastive Learning (AAAI 2024 · similarity 0.90)
- S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning (ICML 2024 · similarity 0.90)
- Community-Invariant Graph Contrastive Learning (ICML 2024 · similarity 0.90)
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.
