Research map / Graph learning / GNN architectures
Is Distance Matrix Enough for Geometric Deep Learning?
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 2-F-DisGNN instead of DimeNet | MD17 force prediction · MD17 | average improvement over DimeNet: 69.68% | Helped |
| Use 3-E-DisGNN instead of GemNet | MD17 force prediction · MD17 | average improvement over DimeNet: 65.27% | Helped |
| Add edge weight to 2-DisGNN (ablation) | 2-DisGNN · MD17 | MAE: 39.8% | Helped |
| Add the full edge representation, including tuple representations (ablation) | 2-DisGNN · MD17 | MAE: 39.8% | Helped |
| Add tuple representations to edge weight (ablation) | 2-e-DisGNN · MD17 | MAE: 3.8% | Helped |
Closest papers by meaning
- On the Completeness of Invariant Geometric Deep Learning Models (ICLR 2025 · similarity 0.90)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.88)
- Simplicial Representation Learning with Neural $k$-Forms (ICLR 2024 · similarity 0.88)
- Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs (NeurIPS 2026 · similarity 0.87)
- On the Expressive Power of Sparse Geometric MPNNs (ICLR 2025 · similarity 0.87)
- What do Graph Neural Networks learn? Insights from Tropical Geometry (NeurIPS 2024 · similarity 0.86)
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.