Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
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_ | 1866909200311910400 |
|---|---|
| author | Deng, Bowen Choi, Yunyeong Zhong, Peichen Riebesell, Janosh Anand, Shashwat Li, Zhuohan Jun, KyuJung Persson, Kristin A. Ceder, Gerbrand |
| author_facet | Deng, Bowen Choi, Yunyeong Zhong, Peichen Riebesell, Janosh Anand, Shashwat Li, Zhuohan Jun, KyuJung Persson, Kristin A. Ceder, Gerbrand |
| contents | Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets, providing opportunities for both ready-to-use universal force fields and robust foundations for downstream machine learning refinements. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force under-prediction in a series of atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, phonon vibration modes, ion migration barriers, and general high-energy states.
We find that the PES softening behavior originates from a systematic underprediction error of the PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. We demonstrate that the PES softening issue can be effectively rectified by fine-tuning with a single additional data point. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. This result rationalizes the data-efficient fine-tuning performance boost commonly observed with foundational MLIPs. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07105 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning Deng, Bowen Choi, Yunyeong Zhong, Peichen Riebesell, Janosh Anand, Shashwat Li, Zhuohan Jun, KyuJung Persson, Kristin A. Ceder, Gerbrand Materials Science Artificial Intelligence Machine Learning Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have seen the emergence of universal MLIPs (uMLIPs) that are pre-trained on diverse materials datasets, providing opportunities for both ready-to-use universal force fields and robust foundations for downstream machine learning refinements. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force under-prediction in a series of atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, phonon vibration modes, ion migration barriers, and general high-energy states. We find that the PES softening behavior originates from a systematic underprediction error of the PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. We demonstrate that the PES softening issue can be effectively rectified by fine-tuning with a single additional data point. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. This result rationalizes the data-efficient fine-tuning performance boost commonly observed with foundational MLIPs. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs. |
| title | Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning |
| topic | Materials Science Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.07105 |