Towards Improved Quantum Machine Learning for Molecular Force Fields

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Couzinié, Yannick, Daimon, Shunsuke, Nishi, Hirofumi, Ito, Natsuki, Harazono, Yusuke, Matsushita, Yu-ichiro
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915689018687488
author Couzinié, Yannick
Daimon, Shunsuke
Nishi, Hirofumi
Ito, Natsuki
Harazono, Yusuke
Matsushita, Yu-ichiro
author_facet Couzinié, Yannick
Daimon, Shunsuke
Nishi, Hirofumi
Ito, Natsuki
Harazono, Yusuke
Matsushita, Yu-ichiro
contents This study explores the use of equivariant quantum neural networks (QNN) for generating molecular force fields, focusing on the rMD17 dataset. We consider a QNN architecture based on previous research and point out shortcomings in the parametrization of the atomic environments. These shortcomings limit its expressivity as an interatomic potential and precludes transferability between molecules. We propose a revised QNN architecture that addresses these shortcomings. While both QNNs show promise in force prediction, with the revised architecture showing improved accuracy, they struggle with energy prediction. Further, both QNNs architectures fail to demonstrate a meaningful scaling law of decreasing errors with increasing training data. These findings highlight the challenges of scaling QNNs for complex molecular systems and emphasize the need for improved encoding strategies, regularization techniques, and hybrid quantum-classical approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Improved Quantum Machine Learning for Molecular Force Fields
Couzinié, Yannick
Daimon, Shunsuke
Nishi, Hirofumi
Ito, Natsuki
Harazono, Yusuke
Matsushita, Yu-ichiro
Chemical Physics
Quantum Physics
This study explores the use of equivariant quantum neural networks (QNN) for generating molecular force fields, focusing on the rMD17 dataset. We consider a QNN architecture based on previous research and point out shortcomings in the parametrization of the atomic environments. These shortcomings limit its expressivity as an interatomic potential and precludes transferability between molecules. We propose a revised QNN architecture that addresses these shortcomings. While both QNNs show promise in force prediction, with the revised architecture showing improved accuracy, they struggle with energy prediction. Further, both QNNs architectures fail to demonstrate a meaningful scaling law of decreasing errors with increasing training data. These findings highlight the challenges of scaling QNNs for complex molecular systems and emphasize the need for improved encoding strategies, regularization techniques, and hybrid quantum-classical approaches.
title Towards Improved Quantum Machine Learning for Molecular Force Fields
topic Chemical Physics
Quantum Physics
url https://arxiv.org/abs/2505.03213