INN-FF: A Scalable and Efficient Machine Learning Potential for Molecular Dynamics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918032219045888 |
|---|---|
| author | Mehereen, Taskin Saha, Sourav Jaigirdar, Intesar Jawad Park, Chanwook |
| author_facet | Mehereen, Taskin Saha, Sourav Jaigirdar, Intesar Jawad Park, Chanwook |
| contents | The ability to accurately model interatomic interactions in large-scale systems is fundamental to understanding a wide range of physical and chemical phenomena, from drug-protein binding to the behavior of next-generation materials. While machine learning interatomic potentials (MLIPs) have made it possible to achieve ab initio-level accuracy at significantly reduced computational cost, they still require very large training datasets and incur substantial training time and expense. In this work, we propose the Interpolating Neural Network Force Field (INN-FF), a novel framework that merges interpolation theory and tensor decomposition with neural network architectures to efficiently construct molecular dynamics potentials from limited quantum mechanical data. Interpolating Neural Networks (INNs) achieve comparable or better accuracy than traditional multilayer perceptrons (MLPs) while requiring orders of magnitude fewer trainable parameters. On benchmark datasets such as liquid water and rMD17, INN-FF not only matches but often surpasses state-of-the-art accuracy by an order of magnitude, while achieving significantly lower error when trained on smaller datasets. These results suggest that INN-FF offers a promising path toward building efficient and scalable machine-learned force fields. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18141 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | INN-FF: A Scalable and Efficient Machine Learning Potential for Molecular Dynamics Mehereen, Taskin Saha, Sourav Jaigirdar, Intesar Jawad Park, Chanwook Materials Science Chemical Physics The ability to accurately model interatomic interactions in large-scale systems is fundamental to understanding a wide range of physical and chemical phenomena, from drug-protein binding to the behavior of next-generation materials. While machine learning interatomic potentials (MLIPs) have made it possible to achieve ab initio-level accuracy at significantly reduced computational cost, they still require very large training datasets and incur substantial training time and expense. In this work, we propose the Interpolating Neural Network Force Field (INN-FF), a novel framework that merges interpolation theory and tensor decomposition with neural network architectures to efficiently construct molecular dynamics potentials from limited quantum mechanical data. Interpolating Neural Networks (INNs) achieve comparable or better accuracy than traditional multilayer perceptrons (MLPs) while requiring orders of magnitude fewer trainable parameters. On benchmark datasets such as liquid water and rMD17, INN-FF not only matches but often surpasses state-of-the-art accuracy by an order of magnitude, while achieving significantly lower error when trained on smaller datasets. These results suggest that INN-FF offers a promising path toward building efficient and scalable machine-learned force fields. |
| title | INN-FF: A Scalable and Efficient Machine Learning Potential for Molecular Dynamics |
| topic | Materials Science Chemical Physics |
| url | https://arxiv.org/abs/2505.18141 |