Machine Learning Multiscale Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913161449308160 |
|---|---|
| author | Solé, Àlex Suárez-Dou, Sergio Mosella-Montoro, Albert Gómez-Coca, Silvia Ruiz, Eliseo Tkatchenko, Alexandre Ruiz-Hidalgo, Javier |
| author_facet | Solé, Àlex Suárez-Dou, Sergio Mosella-Montoro, Albert Gómez-Coca, Silvia Ruiz, Eliseo Tkatchenko, Alexandre Ruiz-Hidalgo, Javier |
| contents | Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25710 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine Learning Multiscale Interactions Solé, Àlex Suárez-Dou, Sergio Mosella-Montoro, Albert Gómez-Coca, Silvia Ruiz, Eliseo Tkatchenko, Alexandre Ruiz-Hidalgo, Javier Chemical Physics Materials Science Machine Learning Computational Physics Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models. |
| title | Machine Learning Multiscale Interactions |
| topic | Chemical Physics Materials Science Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2605.25710 |