Research map / Graph learning / Graph self-supervised learning
Co-Modality Graph Contrastive Learning for Imbalanced Node Classification
Yiyue Qian, Chunhui Zhang, Yiming Zhang, Qianlong Wen, Yanfang Ye, Chuxu Zhang
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 co-modality GCL (ablation) | CM-GCL · AMiner D0.1 | F1: 56.21 -> 74.78 | Improved |
| add co-modality GCL (ablation) | CM-GCL · AMiner D0.1 | AUC: 92.34 -> 96.42 | Improved |
| add co-modality GCL (ablation) | CM-GCL · Instagram D0.1 | F1: 42.62 -> 51.24 | Improved |
| add co-modality GCL (ablation) | CM-GCL · Instagram D0.1 | AUC: 81.45 -> 89.14 | Improved |
| add network pruning (ablation) | CM-GCL · AMiner D0.1 | F1: 72.42 -> 74.78 | Improved |
| add network pruning (ablation) | CM-GCL · Instagram D0.1 | F1: 48.53 -> 51.24 | Improved |
| add network pruning (ablation) | CM-GCL · Instagram D0.1 | AUC: 87.18 -> 89.14 | Improved |
| add intra-modality GCL (ablation) | CM-GCL · AMiner D0.1 | F1: 72.51 -> 74.78 | Improved |
| add intra-modality GCL (ablation) | CM-GCL · Instagram D0.1 | AUC: 87.69 -> 89.14 | Improved |
| CM-GCL instead of GraphCL | GraphCL · YelpChi D0.01 | F1: 50.23 -> 50.45 | No clear effect |
| CM-GCL instead of GraphSMOTE at extreme imbalance | GraphSMOTE · Github D0.01 | F1: 45.97 -> 45.89 | No clear effect |
| CM-GCL instead of GraphSMOTE at extreme imbalance | GraphSMOTE · Instagram D0.01 | F1: 23.48 -> 22.47 | Hurt |
Closest papers by meaning
- ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification (AAAI 2023 · similarity 0.93)
- Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling (AAAI 2025 · similarity 0.92)
- ReGCL: Rethinking Message Passing in Graph Contrastive Learning (AAAI 2024 · similarity 0.91)
- Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning (AAAI 2024 · similarity 0.90)
- Beyond Homophily: Graph Contrastive Learning with Macro-Micro Message Passing (AAAI 2025 · similarity 0.90)
- S3GCL: Spectral, Swift, Spatial 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.
