Research map / Graph learning / GNN architectures
Equivariant Networks for Crystal Structures
Sékou-Oumar Kaba, Siamak Ravanbakhsh
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 S_Lambda (more symmetry than needed) instead of P1bar (ablation) | ECN · Materials Project E_F | MAE: 0.303 -> 0.281 | Improved |
| use S_Lambda instead of P1bar (ablation) | ECN · Materials Project formation energy | MAE: 0.052 -> 0.046 | Improved |
| use S_Lambda instead of P1bar (ablation) | ECN · Materials Project band gap | MAE: 0.44 -> 0.390 | Improved |
| use S_Lambda instead of P1bar (ablation) | ECN · Materials Project nonmetal precision | precision: 84 -> 83.2 | Hurt |
| ECN-S_Lambda versus retrained CGCNN | ECN · Materials Project E_F | MAE: 0.307 -> 0.281 | Improved |
| ECN-S_Lambda versus retrained CGCNN | ECN · Materials Project formation energy | MAE: 0.048 -> 0.046 | Improved |
| ECN-S_Lambda versus retrained MEGNet | ECN · Materials Project band gap | MAE: 0.434 -> 0.390 | Improved |
| ECN-S_Lambda versus retrained CGCNN | ECN · Materials Project metal precision | precision: 81.2 -> 79.8 | Hurt |
| ECN-S_Lambda versus CGCNN | ECN · Perov-5 heat of formation | MAE: 0.047 -> 0.038 | Improved |
| ECN-S_Lambda versus MEGNet | ECN · Perov-5 heat of formation | MAE: 0.059 -> 0.038 | Improved |
| add Hubbard-U feature (ablation) | ECN-S_Lambda · Materials Project band gap | MAE: 0.390 -> 0.368 | Improved |
| add Hubbard-U feature (ablation) | ECN-S_Lambda · Materials Project formation energy | MAE: 0.046 -> 0.052 | Hurt |
Closest papers by meaning
- A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction (ICML 2024 · similarity 0.90)
- Equivariant Diffusion for Crystal Structure Prediction (ICML 2024 · similarity 0.90)
- Conformal Crystal Graph Transformer with Robust Encoding of Periodic Invariance (AAAI 2024 · similarity 0.88)
- Learning the Electronic Hamiltonian of Large Atomic Structures (ICML 2025 · similarity 0.88)
- WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry (ICML 2025 · similarity 0.88)
- Space Group Equivariant Crystal Diffusion (NeurIPS 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.
