홈 › Papers

Ensemble Knowledge Distillation for Machine Learning Interatomic Potentials

2025-03-18 · Sakib Matin, Emily Shinkle, Yulia Pimonova, Galen T. Craven, Aleksandra Pachalieva, Ying Wai Li, Kipton Barros, Nicholas Lubbers

The quality of machine learning interatomic potentials (MLIPs) strongly depends on the quantity of training data as well as the quantum chemistry (QC) level of theory used. Datasets generated with high-fidelity QC methods are typically restricted to small molecules and may be missing energy gradients, which make it difficult to train accurate MLIPs. We present an ensemble knowledge distillation (EKD) method to improve MLIP accuracy when trained to energy-only datasets. First, multiple teacher models are trained to QC energies and then generate atomic forces for all configurations in the dataset. Next, the student MLIP is trained to both QC energies and to ensemble-averaged forces generated by the teacher models. We apply this workflow on the ANI-1ccx dataset where the configuration energies computed at the coupled cluster level of theory. The resulting student MLIPs achieve new state-of-the-art accuracy on the COMP6 benchmark and show improved stability for molecular dynamics simulations.

📄 PDF Abstract BibTeX arXiv:2503.14293

Code (0)

등록된 구현이 없습니다.

Tasks

Atomic ForcesKnowledge Distillation Molecular Property PredictionProperty Prediction

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Interpretable Ensemble Learning for Materials Property Prediction with Classical Interatomic Potentials: Carbon as an Example

2023-07-24 · Xinyu Jiang, Haofan Sun, Kamal Choudhary, Houlong Zhuang 외

Machine learning (ML) is widely used to explore crystal materials and predict their properties. However, the training is time-consuming for deep-learning models, and the regression process is a black box that is hard to …

Ensemble Learning Formation Energy Property Prediction regression

BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials

2026-10-01 · Laura Zichi, Gil Harari, Chuin Wei Tan, Marc L. Descoteaux 외 arxiv

Equivariant machine learning interatomic potentials (MLIPs) have revolutionized atomistic modeling, but accurate treatment of complex materials and molecular systems demands expensive models. This limits simulation lengt…

Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction

2023-06-12 · Yuchao Lin, Keqiang Yan, Youzhi Luo, Yi Liu 외

We study property prediction for crystal materials. A crystal structure consists of a minimal unit cell that is repeated infinitely in 3D space. How to accurately represent such repetitive structures in machine learning …

Band Gap Formation Energy Property Prediction Representation Learning

Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces

2023-05-10 · Jonas Busk, Mikkel N. Schmidt, Ole Winther, Tejs Vegge 외

Inexpensive machine learning potentials are increasingly being used to speed up structural optimization and molecular dynamics simulations of materials by iteratively predicting and applying interatomic forces. In these …

Graph Neural Network

Evaluation of uncertainty estimations for Gaussian process regression based machine learning interatomic potentials

2024-10-27 · Matthias Holzenkamp, Dongyu Lyu, Ulrich Kleinekathöfer, Peter Zaspel

Uncertainty estimations for machine learning interatomic potentials (MLIPs) are crucial for quantifying model error and identifying informative training samples in active learning strategies. In this study, we evaluate u…

Active Learning GPR