Coarse-grained graph architectures for all-atom force predictions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kang, Sungwoo, Chae, Jinwoong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910210017198080
author Kang, Sungwoo
Chae, Jinwoong
author_facet Kang, Sungwoo
Chae, Jinwoong
contents We introduce a machine-learning framework termed coarse-grained all-atom force field (CGAA-FF), which incorporates coarse-grained message passing within an all-atom force field using equivariant nature of graph models. The CGAA-FF model employs grain embedding to encode atomistic coordinates into nodes representing grains rather than individual atoms, enabling predictions of both grain-level energies and atom-level forces. Tested on EC/EMC organic electrolytes and RDX crystalline and disordered phases, CGAA-FF achieves 0.201 and 0.253 eV A-1, respectively, while providing about 10-fold and 5-fold higher computational speed and memory efficiency, respectively, than conventional MLIPs. Since this CGAA framework can be integrated into any equivariant architecture, we believe this work opens the door to efficient all-atom simulations of soft-matter systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01058
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coarse-grained graph architectures for all-atom force predictions
Kang, Sungwoo
Chae, Jinwoong
Materials Science
Soft Condensed Matter
We introduce a machine-learning framework termed coarse-grained all-atom force field (CGAA-FF), which incorporates coarse-grained message passing within an all-atom force field using equivariant nature of graph models. The CGAA-FF model employs grain embedding to encode atomistic coordinates into nodes representing grains rather than individual atoms, enabling predictions of both grain-level energies and atom-level forces. Tested on EC/EMC organic electrolytes and RDX crystalline and disordered phases, CGAA-FF achieves 0.201 and 0.253 eV A-1, respectively, while providing about 10-fold and 5-fold higher computational speed and memory efficiency, respectively, than conventional MLIPs. Since this CGAA framework can be integrated into any equivariant architecture, we believe this work opens the door to efficient all-atom simulations of soft-matter systems.
title Coarse-grained graph architectures for all-atom force predictions
topic Materials Science
Soft Condensed Matter
url https://arxiv.org/abs/2505.01058