Research map / Graph learning / GNN architectures
A new perspective on building efficient and expressive 3D equivariant graph neural networks
weitao Du, Yuanqi Du, Limei Wang, Dieqiao Feng, Guifeng Wang, Shuiwang Ji, Carla P Gomes, Zhi-Ming Ma
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 |
|---|---|---|---|
| propose LEFTNet with local substructure and frame transition encoding vs prior SOTA | QM9 100k/18k/13k split · QM9 | MAE (12 properties) | Improved |
| LEFTNet vs prior methods on second QM9 split | QM9 110k/10k/11k split · QM9 | MAE (12 properties) | Improved |
| LEFTNet vs prior methods on QM9 energy gap | QM9 · QM9 Delta epsilon | MAE (meV): 33 -> 40 | Hurt |
| LEFTNet vs baselines on MD17 force prediction with WoFE=100 | MD17 · MD17 | force MAE | Improved |
| LEFTNet vs baselines on MD17 force prediction with WoFE=1000 | MD17 · MD17 | force MAE | Improved |
| add local 3D substructure encoding (LSE) to model without LSE and FTE (ablation) | LEFTNet · QM9 and MD17 | MAE | Improved |
| add frame transition encoding (FTE) on top of LSE (ablation) | LEFTNet · QM9 and MD17 | MAE | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Equiformer — Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs (ICLR 2023) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? (NeurIPS 2024 · similarity 0.90)
- On Explaining Equivariant Graph Networks via Improved Relevance Propagation (ICML 2025 · similarity 0.89)
- On the Generalization of Equivariant Graph Neural Networks (ICML 2024 · similarity 0.89)
- Universally Invariant Learning in Equivariant GNNs (NeurIPS 2025 · similarity 0.89)
- Large Language-Geometry Model: When LLM meets Equivariance (ICML 2025 · similarity 0.88)
- On the Expressive Power of Sparse Geometric MPNNs (ICLR 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.
