Research map / Graph learning / Graph self-supervised learning
Topology-Imbalance Learning for Semi-Supervised Node Classification
Deli Chen, Yankai Lin, Guangxiang Zhao, Xuancheng Ren, Peng Li, Jie Zhou, Xu Sun
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 Totoro-based adaptive node reweighting | GCN · CORA | Weighted-F1: 79.1 $\pm$1.1 -> 79.8$^{**}$ $\pm$0.9 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · CiteSeer | Weighted-F1: 66.2 $\pm$1.0 -> 66.9$^{*}$ $\pm$1.1 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · PubMed | Weighted-F1: 74.6 $\pm$2.1 -> 76.1$^{**}$ $\pm$1.5 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · Photo | Weighted-F1: 86.8 $\pm$2.0 -> 87.7$^{**}$ $\pm$2.2 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · Computers | Weighted-F1: 74.2 $\pm$2.6 -> 74.7$^{*}$ $\pm$2.2 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · CORA | Macro-F1: 77.8 $\pm$1.5 -> 78.6$^{**}$ $\pm$1.2 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · CiteSeer | Macro-F1: 62.0 $\pm$1.3 -> 62.8$^{*}$ $\pm$1.4 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · PubMed | Macro-F1: 74.7 $\pm$1.9 -> 76.1$^{**}$ $\pm$1.8 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · Photo | Macro-F1: 84.7 $\pm$1.7 -> 85.4$^{**}$ $\pm$1.9 | Improved |
| Add Totoro-based adaptive node reweighting | GCN · Computers | Macro-F1: 73.6 $\pm$2.9 -> 74.5$^{**}$ $\pm$2.3 | Improved |
| Use cosine annealing rather than the tested linear or piece-wise weight schedules (ablation) | ReNode · Semi-supervised node classification | model performance | Improved |
| Use Totoro-rank-based cosine weighting instead of weighting from original Totoro values (ablation) | ReNode · Semi-supervised node classification | model performance | Improved |
Closest papers by meaning
- Class-Imbalanced Graph Learning without Class Rebalancing (ICML 2024 · similarity 0.91)
- Geometric Imbalance in Semi-Supervised Node Classification (NeurIPS 2025 · similarity 0.90)
- Cluster-guided Contrastive Class-imbalanced Graph Classification (AAAI 2025 · similarity 0.88)
- Automated Loss function Search for Class-imbalanced Node Classification (ICML 2024 · similarity 0.88)
- Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph (ICML 2025 · similarity 0.88)
- Subgraph Invariant Learning Towards Large-Scale Graph Node Classification (AAAI 2025 · similarity 0.87)
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.
