Active learning strategies for atomic cluster expansion models

2022/12/16 by Yury Lysogorskiy, Anton Bochkarev, Lysogorskiy, Yury +5 · 8 citations
Chemistry · Materials Science · #Electron and X-Ray Spectroscopy Techniques #FOS: Physical sciences #Inorganic Chemistry and Materials #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci)

paper · pdf · doi:10.48550/arxiv.2212.08716

openalex publication_date 2022/12/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The atomic cluster expansion (ACE) was proposed recently as a new class of data-driven interatomic potentials with a formally complete basis set. Since the development of any interatomic potential requires a careful selection of training data and thorough validation, an automation of the construction of the training dataset as well as an indication of a model's uncertainty are highly desirable. In this work, we compare the performance of two approaches for uncertainty indication of ACE models based on the D-optimality criterion and ensemble learning. While both approaches show comparable predictions, the extrapolation grade based on the D-optimality (MaxVol algorithm) is more computationally efficient. In addition, the extrapolation grade indicator enables an active exploration of new structures, opening the way to the automated discovery of rare-event configurations. We demonstrate that active learning is also applicable to explore local atomic environments from large-scale MD simulations.

Cited by

• Machine-Learned Interatomic Potentials for Structural and Defect Properties of YBa₂Cu₃O_7-δ
• Atomic cluster expansion potential for the Si-H system
• Macro-Dipole-Constrainted Learning of Atomic Charges for Accurate Electrostatic Potentials at Electrochemical Interfaces
• PASS: Perturbation augmented space group structure sampling for transferable Fe-O machine learning interatomic potential
• Water structuring at stacked graphene interfaces unveiled by machine-learning molecular dynamics
• How Realistic are Idealized Copper Surfaces? A Machine Learning Study of Rough Copper-Water Interfaces
• Machine-learning interatomic potentials achieving CCSD(T) accuracy for systems with extended covalent networks and van der Waals interactions
• Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials

Related

• Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• Graph atomic cluster expansion for foundational machine learning interatomic potentials
• Hyperparameter Optimization for Atomic Cluster Expansion Potentials
• Atomic Cluster Expansion without Self-Interaction