Dataset-aware entropy-maximized active learning for machine-learned interatomic potentials

TL;DR

This paper introduces an entropy-maximized active learning framework that efficiently generates high-quality training data for machine-learned interatomic potentials across diverse materials and phases.

Contribution

The method combines local entropy-driven molecular dynamics with global dataset-aware filtering, enabling broad configuration space coverage and improved learning efficiency.

Findings

Achieves 3-10 times lower energy MAE than random sampling at similar training sizes.

Effective across systems with covalent, metallic, and ionic bonding.

Requires significantly fewer configurations to reach high accuracy.

Abstract

We present an active learning framework for efficiently generating training data for machine-learned interatomic potentials (MLIPs). The method combines local entropy-driven molecular dynamics with global dataset-aware filtering: a per-configuration entropy term biases MD trajectories toward structurally diverse snapshots, while a global entropy measure, the log-determinant of the fingerprint covariance matrix of the entire dataset, selects only those configurations that provide genuinely new information. We employ dual covariance modes (per-atom for disordered structures and per-config for ordered phases) to achieve broad coverage of configuration space. Combined with a pre-trained foundation model (Allegro-OAM-L) and analytical fingerprint gradients from Gaussian overlap matrix eigenvalues, the framework produces high-quality domain-specific potentials with near- or sub-meV/atom accuracy on test data drawn from the same distribution at training-set sizes of order $10^{2}$ to $10^{3}$ entropy-selected DFT-labeled structures. We demonstrate the method on three systems spanning diverse bonding types and pressure-driven phase transitions: carbon (covalent), silicon (covalent/metallic), and NaCl (ionic). In learning curve comparisons against random molecular dynamics sampling at matched training set sizes ($N = 100$ to $800$), evaluated over three independent training-set draws per condition, entropy-driven sampling achieves a factor of approximately $3$ to $10$ lower energy MAE at $N = 800$ on in-distribution holdouts across the three systems, with the magnitude of the gain depending on the bonding type and the size at which the random-MD baseline saturates.