Research map / Graph learning / Graph self-supervised learning
GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GeomGCL instead of the best message-passing baseline | Molecular property prediction · Classification tasks (four datasets) | ROC-AUC: 2.18% | Helped |
| Use GeomGCL instead of the best message-passing baseline | Molecular property prediction · Regression tasks (three datasets) | RMSE: 10.4% | Helped |
| Add 2D-3D geometric contrastive learning to dual-channel GeomMPNN (ablation) | GeomMPNN · Four ablation benchmarks | Property prediction performance | Helped |
| Use both 2D and 3D geometric views rather than only one view (ablation) | GeomGCL · Four ablation benchmarks | Property prediction performance | Helped |
| Use only the 2D geometric message-passing channel (ablation) | GeomGCL · Four ablation benchmarks | Property prediction performance | Hurt |
| Use only the 3D geometric message-passing channel (ablation) | GeomGCL · Four ablation benchmarks | Property prediction performance | Hurt |
| Add the spatial regularizer for 3D angle-domain transformations (ablation) | GeomGCL · Four ablation benchmarks | Property prediction performance | Helped |
| Vary the spatial-regularizer coefficient λ (ablation) | GeomGCL · Parameter analysis | Property prediction performance | Mixed |
Closest papers by meaning
- Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer (ICLR 2025 · similarity 0.89)
- Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism (NeurIPS 2024 · similarity 0.89)
- RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation (ICML 2025 · similarity 0.89)
- HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning (AAAI 2024 · similarity 0.89)
- Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs (NeurIPS 2024 · similarity 0.88)
- Enhancing Molecular Representation Learning Through the Combination of 3D and 2D Graph Machine Learning (Student Abstract) (AAAI 2025 · similarity 0.88)
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.