Research map / Graph learning / Graph algorithms and clustering
Grouping Matrix Based Graph Pooling with Adaptive Number of Clusters
Sung Moon Ko, Sungjun Cho, Dae-Woong Jeong, Sehui Han, Moontae Lee, Honglak Lee
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 GMPool instead of the strongest listed baseline | DMPNN graph pooling · PLQY | RMSE: 0.2123 -> 0.2091 | Improved |
| Use GMPool instead of the strongest listed baseline | DMPNN graph pooling · λmax Solvents | RMSE: 44.48 -> 44.48 | No clear effect |
| Use GMPool instead of the strongest listed baseline | DMPNN graph pooling · λmax Films | RMSE: 35.10 -> 34.34 | Improved |
| Use GMPool instead of the strongest listed baseline | DMPNN graph pooling · pIC50 | RMSE: 0.7839 -> 0.6951 | Improved |
| Use GMPool instead of the strongest listed baseline | DMPNN graph pooling · Tox21 | ROC-AUC: 0.7593 -> 0.7451 | Hurt |
| Use the grouping matrix directly without decomposition (NGMPool) (ablation) | GMPool · PLQY | RMSE: 0.2091 -> 0.2169 | Hurt |
| Use the grouping matrix directly without decomposition (NGMPool) (ablation) | GMPool · λmax Solvents | RMSE: 44.48 -> 38.61 | Improved |
| Use the grouping matrix directly without decomposition (NGMPool) (ablation) | GMPool · λmax Films | RMSE: 34.34 -> 39.82 | Hurt |
| Use the grouping matrix directly without decomposition (NGMPool) (ablation) | GMPool · pIC50 | RMSE: 0.6951 -> 0.7253 | Hurt |
| Use the grouping matrix directly without decomposition (NGMPool) (ablation) | GMPool · Tox21 | ROC-AUC: 0.7451 -> 0.7617 | Improved |
| Allow the model to determine cluster count rather than forcing a fixed count (ablation) | GMPool · PLQY | RMSE | No clear effect |
Closest papers by meaning
- StructPool: Structured Graph Pooling via Conditional Random Fields (ICLR 2020 · similarity 0.89)
- Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.87)
- SkipPool: Improved Sparse Hierarchical Graph Pooling with Differentiable Exploration (AAAI 2025 · similarity 0.85)
- Graph Parsing Networks (ICLR 2024 · similarity 0.85)
- Boosting Graph Pooling with Persistent Homology (NeurIPS 2024 · similarity 0.85)
- ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks (ICML 2025 · similarity 0.84)
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.
