Physics-Informed Weakly Supervised Learning for Interatomic Potentials
Keywords: machine learning interatomic potential, weakly supervised learning, machine learning for science
TL;DR: A new physics-informed, weakly supervised learning approach for training ML models for predicting molecular properties with better accuracy and robustness
Abstract: Machine learning plays an increasingly important role in computational chemistry and materials science, complementing computationally intensive ab initio and first-principles methods. Despite their utility, machine-learning models often lack generalization capability and robustness during atomistic simulations, yielding unphysical energy and force predictions that hinder their real-world applications. We address this challenge by introducing a physics-informed, weakly supervised approach for training machine-learned interatomic potentials (MLIPs). We introduce two novel loss functions, extrapolating the potential energy via a Taylor expansion and using the concept of conservative forces. Our approach improves the accuracy of MLIPs applied to training tasks with sparse training data sets and reduces the need for pre-training computationally demanding models with large data sets. Particularly, we perform extensive experiments demonstrating reduced energy and force errors---often lower by a factor of two---for various baseline models and benchmark data sets. Moreover, we demonstrate improved robustness during MD simulations of the MLIP models trained with the proposed weakly supervised loss.
Finally, we show that our approach facilitates MLIPs' training in a setting where the computation of forces is infeasible at the reference level, such as those employing complete-basis-set extrapolation. An implementation of our method and scripts for executing experiments are available at \url{https://anonymous.4open.science/r/PICPS-ML4Sci-1E8F}.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6098
Loading