Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Contrastive Re-Learning for Multi-Graph Multi-Label Classification
Meixia Wang, Yuhai Zhao, Zhengkui Wang, Yejiang Wang, Miaomiao Huang, Fenglong Ma, Fazal Wahab, Wen Shan, Xingwei Wang
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 graph-level contrastive loss L1 (ablation) | PETAL · Dblp(ai) | Average Precision: 0.778 -> 0.780 | Improved |
| add bag-level contrastive loss L2 (ablation) | PETAL · Dblp(ai) | Average Precision: 0.772 -> 0.780 | Improved |
| add cross-granularity bag-graph loss L3 (ablation) | PETAL · Dblp(ai) | Average Precision: 0.752 -> 0.780 | Improved |
| add contrastive re-learning to generate augmentation-free positives (ablation) | PETAL · Dblp(ai) | Average Precision: 0.430 -> 0.780 | Improved |
| add label prototypes C (ablation) | PETAL · Dblp(ai) | Average Precision: 0.721 -> 0.780 | Improved |
| add contrastive re-learning (ablation) | PETAL · Dblp(ai) | Macro-F1: 0.109 -> 0.386 | Improved |
| use PETAL instead of supervised cfMGNML | cfMGNML · Dblp(ai) | Average Precision: 0.749 -> 0.780 | Improved |
| use PETAL instead of supervised cfMGNML | cfMGNML · MSRC v2 | Average Precision: 0.659 -> 0.696 | Improved |
| use PETAL instead of graph contrastive learning baseline PaGCL | PaGCL · Dblp(ai) | Average Precision: 0.455 -> 0.739 | Improved |
| use PETAL instead of PaGCL | PaGCL · Dblp(db) | Average Precision: 0.470 -> 0.713 | Improved |
| use PETAL instead of PaGCL | PaGCL · VOC12 | One Error: 0.285 -> 0.278 | No clear effect |
Closest papers by meaning
- Multi-Label Supervised Contrastive Learning (AAAI 2024 · similarity 0.89)
- Use All the Labels: A Hierarchical Multi-Label Contrastive Learning Framework (CVPR 2022 · similarity 0.88)
- A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning (NeurIPS 2021 · similarity 0.88)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.87)
- Weakly-Supervised Contrastive Learning for Imprecise Class Labels (ICML 2025 · similarity 0.87)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.86)
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.
