Research map / Point clouds / Point cloud classification
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
Oliver Thorsten Unke, Mihail Bogojeski, Michael Gastegger, Mario Geiger, Tess Smidt, Klaus Robert Muller
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 |
|---|---|---|---|
| replace non-equivariant SchNOrb with SE(3)-equivariant PhiSNet | wavefunction prediction · Water | Kohn-Sham error [10^-6 Eh]: 165.4 -> 17.59 | Improved |
| replace SchNOrb with PhiSNet | wavefunction prediction · Uracil | Kohn-Sham error [10^-6 Eh]: 227.8 -> 10.73 | Improved |
| replace SchNOrb with PhiSNet | wavefunction prediction · Aspirin | orbital energy error [10^-6 Eh]: 48689 -> 176.6 | Improved |
| replace SchNOrb with PhiSNet | wavefunction prediction · Aspirin | wavefunction cosine similarity: 0.57 -> 0.98 | Improved |
| fine-tune HF-pretrained PhiSNet on CCSD(T) forces | PhiSNet · CCSD(T)/cc-pVTZ energies | energy MAE (µEh): 4266 -> 79 | Improved |
| fine-tune HF-pretrained PhiSNet on CCSD(T) forces | PhiSNet · CCSD(T)/cc-pVTZ forces | force MAE (mEh/a0): 15 -> 0.85 | Improved |
| use PhiSNet-predicted wavefunction as initial SCF guess | DFT/HF solver · iterations | SCF iterations: 56-72% fewer iterations | Improved |
| replace spherical linear layers with plain linear layers when Lin = Lout (ablation) | PhiSNet · accuracy | prediction accuracy | Hurt |
Closest papers by meaning
- Learning Equivariant Non-Local Electron Density Functionals (ICLR 2025 · similarity 0.89)
- Learning the Electronic Hamiltonian of Large Atomic Structures (ICML 2025 · similarity 0.89)
- High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction (NeurIPS 2025 · similarity 0.88)
- Enhancing the Scalability and Applicability of Kohn-Sham Hamiltonians for Molecular Systems (ICLR 2025 · similarity 0.88)
- Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing (NeurIPS 2024 · similarity 0.88)
- EDBench: Large-Scale Electron Density Data for Molecular Modeling (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.
