Research map / Graph learning / Graph self-supervised learning
One for Two: A Unified Framework for Imbalanced Graph Classification via Dynamic Balanced Prototype
Guanjun Wang, Binwu Wang, Jiaming Ma, Zhengyang Zhou, Pengkun Wang, Xu Wang, Yang 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 |
|---|---|---|---|
| use uniform prior instead of Zipf for prototype load balancing (ablation) | UniImb · PROTEINS Macro-F1 | Macro-F1: 67.80 -> 70.44 | Improved |
| use uniform prior instead of Exponential (ablation) | UniImb · PROTEINS Macro-F1 | Macro-F1: 66.45 -> 70.44 | Improved |
| use uniform prior instead of Poisson (ablation) | UniImb · D&D Macro-F1 | Macro-F1: 41.62 -> 46.63 | Improved |
| add UniImb to GIN | GIN · D&D (class imbalance) | Macro-F1: 9.99 -> 46.63 | Improved |
| add UniImb to GCN | GCN · D&D (class imbalance) | Macro-F1: 7.20 -> 44.85 | Improved |
| add UniImb to GraphGPS | GraphGPS · D&D (class imbalance) | Macro-F1: 10.12 -> 40.17 | Improved |
| add UniImb to Graph-Mamba | Graph-Mamba · D&D (class imbalance) | Macro-F1: 4.99 -> 42.18 | Improved |
| add UniImb to GIN | GIN · IMDB-MULTI (class imbalance) | Macro-F1: 13.25 -> 33.45 | Improved |
| add dynamic balanced prototype (DBP) module (ablation) | UniImb · class and topological imbalance datasets | Macro-F1 | Improved |
| add graph topology encoding (ablation) | UniImb · class and topological imbalance datasets | Macro-F1 | Improved |
| add load balancing optimization (BalOpt) (ablation) | UniImb · class-imbalanced datasets | Macro-F1 | Improved |
| add imbalanced feature mixup and graph perturbation (ablation) | UniImb · class and topological imbalance datasets | Macro-F1 | Improved |
Closest papers by meaning
- Class-Imbalanced Graph Learning without Class Rebalancing (ICML 2024 · similarity 0.91)
- Cluster-guided Contrastive Class-imbalanced Graph Classification (AAAI 2025 · similarity 0.89)
- IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning (ICLR 2025 · similarity 0.88)
- Automated Loss function Search for Class-imbalanced Node Classification (ICML 2024 · similarity 0.86)
- Geometric Imbalance in Semi-Supervised Node Classification (NeurIPS 2025 · similarity 0.86)
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models (NeurIPS 2025 · similarity 0.85)
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.
