Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Harmonic Molecular Representations on Riemannian Manifold
Yiqun Wang, Yuning Shen, Shi Chen, Lihao Wang, Fei YE, Hao Zhou
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 HMR instead of SEGNN | QM9 property regression · QM9 | MAE α: .060 -> .102 | Hurt |
| Use HMR instead of SEGNN | QM9 property regression · QM9 | MAE Δε: 42 -> 59 | Hurt |
| Use HMR instead of SEGNN | QM9 property regression · QM9 | MAE ε_HOMO: 24 -> 37 | Hurt |
| Use HMR instead of SEGNN | QM9 property regression · QM9 | MAE μ: .023 -> .037 | Hurt |
| Use HMR instead of SEGNN | QM9 property regression · QM9 | MAE Cν: .031 -> .040 | Hurt |
| Use HMR (Top 1) instead of EquiDock | Rigid docking · Docking Benchmark 5.5 | Success rate (≥ Acceptable): 0.00 -> 0.28 | Improved |
| Include the top three predicted binding-site pairs rather than only the top pair | HMR rigid docking · Docking Benchmark 5.5 | Success rate (≥ Acceptable): 0.28 -> 0.33 | Improved |
| Add geometric surface features (ablation) | HMR QM9 property regression · QM9 | MAE | No clear effect |
| Add chemical information (ablation) | HMR rigid docking · Docking Benchmark 5.5 | Docking performance | Improved |
| Add harmonic message passing (ablation) | HMR · Docking task | Model effectiveness | Improved |
Closest papers by meaning
- HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning (AAAI 2024 · similarity 0.88)
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks (ICLR 2024 · similarity 0.87)
- Enhancing Molecular Representation Learning Through the Combination of 3D and 2D Graph Machine Learning (Student Abstract) (AAAI 2025 · similarity 0.86)
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks (ICML 2024 · similarity 0.86)
- GeoMFormer: A General Architecture for Geometric Molecular Representation Learning (ICML 2024 · similarity 0.85)
- Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling (ICML 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.
