Online Test-time Adaptation for Interatomic Potentials
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911876569366528 |
|---|---|
| author | Cui, Taoyong Tang, Chenyu Zhou, Dongzhan Li, Yuqiang Gong, Xingao Ouyang, Wanli Su, Mao Zhang, Shufei |
| author_facet | Cui, Taoyong Tang, Chenyu Zhou, Dongzhan Li, Yuqiang Gong, Xingao Ouyang, Wanli Su, Mao Zhang, Shufei |
| contents | Machine learning interatomic potentials (MLIPs) enable more efficient molecular dynamics (MD) simulations with ab initio accuracy, which have been used in various domains of physical science. However, distribution shift between training and test data causes deterioration of the test performance of MLIPs, and even leads to collapse of MD simulations. In this work, we propose an online Test-time Adaptation Interatomic Potential (TAIP) framework to improve the generalization on test data. Specifically, we design a dual-level self-supervised learning approach that leverages global structure and atomic local environment information to align the model with the test data. Extensive experiments demonstrate TAIP's capability to bridge the domain gap between training and test dataset without additional data. TAIP enhances the test performance on various benchmarks, from small molecule datasets to complex periodic molecular systems with various types of elements. Remarkably, it also enables stable MD simulations where the corresponding baseline models collapse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08308 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online Test-time Adaptation for Interatomic Potentials Cui, Taoyong Tang, Chenyu Zhou, Dongzhan Li, Yuqiang Gong, Xingao Ouyang, Wanli Su, Mao Zhang, Shufei Computational Physics Machine learning interatomic potentials (MLIPs) enable more efficient molecular dynamics (MD) simulations with ab initio accuracy, which have been used in various domains of physical science. However, distribution shift between training and test data causes deterioration of the test performance of MLIPs, and even leads to collapse of MD simulations. In this work, we propose an online Test-time Adaptation Interatomic Potential (TAIP) framework to improve the generalization on test data. Specifically, we design a dual-level self-supervised learning approach that leverages global structure and atomic local environment information to align the model with the test data. Extensive experiments demonstrate TAIP's capability to bridge the domain gap between training and test dataset without additional data. TAIP enhances the test performance on various benchmarks, from small molecule datasets to complex periodic molecular systems with various types of elements. Remarkably, it also enables stable MD simulations where the corresponding baseline models collapse. |
| title | Online Test-time Adaptation for Interatomic Potentials |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2405.08308 |