Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spaces

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sanocki, Michal, Zavadlav, Julija
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912974118060032
author Sanocki, Michal
Zavadlav, Julija
author_facet Sanocki, Michal
Zavadlav, Julija
contents The vastness of chemical space makes generalization a central challenge in the development of machine learning interatomic potentials (MLIPs). While MLIPs could enable large-scale atomistic simulations with near-quantum accuracy, their usefulness is often limited by poor transferability to out-of-distribution samples. Here, we systematically evaluate different MLIP architectures with long-range corrections across diverse chemical spaces and show that such schemes are essential, not only for improving in-distribution performance but, more importantly, for enabling significant gains in transferability to unseen regions of chemical space. To enable a more rigorous benchmarking, we introduce biased train-test splitting strategies, which explicitly test the model performance in significantly different regions of chemical space. Together, our findings highlight the importance of long-range modeling for achieving generalizable MLIPs and provide a framework for diagnosing systematic failures across chemical space. Although we demonstrate our methodology on metal-organic frameworks, it is broadly applicable to other materials, offering insights into the design of more robust and transferable MLIPs.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10989
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spaces
Sanocki, Michal
Zavadlav, Julija
Chemical Physics
Machine Learning
The vastness of chemical space makes generalization a central challenge in the development of machine learning interatomic potentials (MLIPs). While MLIPs could enable large-scale atomistic simulations with near-quantum accuracy, their usefulness is often limited by poor transferability to out-of-distribution samples. Here, we systematically evaluate different MLIP architectures with long-range corrections across diverse chemical spaces and show that such schemes are essential, not only for improving in-distribution performance but, more importantly, for enabling significant gains in transferability to unseen regions of chemical space. To enable a more rigorous benchmarking, we introduce biased train-test splitting strategies, which explicitly test the model performance in significantly different regions of chemical space. Together, our findings highlight the importance of long-range modeling for achieving generalizable MLIPs and provide a framework for diagnosing systematic failures across chemical space. Although we demonstrate our methodology on metal-organic frameworks, it is broadly applicable to other materials, offering insights into the design of more robust and transferable MLIPs.
title Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spaces
topic Chemical Physics
Machine Learning
url https://arxiv.org/abs/2512.10989