期刊
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
卷 18, 期 9, 页码 5559-5567出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jctc.2c00102
关键词
-
资金
- National Science Foundation of China [11871110, 12122103, 12122401, 12074007]
- DOE [DE-SC0019394]
- Beijing Academy of Artificial Intelligence (BAAI)
- Institute of Computing Technology [CARCH5101, 55E061100]
- National Science Foundation of China [11871110, 12122103, 12122401, 12074007]
- DOE [DE-SC0019394]
- Beijing Academy of Artificial Intelligence (BAAI)
- Institute of Computing Technology [CARCH5101, 55E061100]
This article introduces a model compression scheme to enhance the performance of deep learning-based potential energy surface models. Through testing different physical properties of various systems, the accuracy of this compression scheme is demonstrated.
Machine-learning-based interatomic potential energy surface (PES) models are revolutionizing the field of molecular modeling. However, although much faster than electronic structure schemes, these models suffer from costly computations via deep neural networks to predict the energy and atomic forces, resulting in lower running efficiency as compared to the typical empirical force fields. Herein, we report a model compression scheme for boosting the performance of the Deep Potential (DP) model, a deep learning-based PES model. This scheme, we call DP Compress, is an efficient postprocessing step after the training of DP models (DP Train). DP Compress combines several DP-specific compression techniques, which typically speed up DP-based molecular dynamics simulations by an order of magnitude faster and consume an order of magnitude less memory. We demonstrate that DP Compress is sufficiently accurate by testing a variety of physical properties of Cu, H2O, and Al-Cu-Mg systems. DP Compress applies to both CPU and GPU machines and is publicly available online.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据