Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systems

TL;DR

This paper introduces an active learning framework for training machine-learned interatomic potentials efficiently across various materials, reducing the need for costly calculations and providing practical guidelines for data-efficient model development.

Contribution

It develops a novel active learning approach using diversity sampling and uncertainty quantification, demonstrating improved efficiency over baseline methods across multiple material systems.

Findings

Diversity sampling outperforms random sampling in accuracy and efficiency.

The approach reduces labeled data requirements by 5-13%.

The pipeline is fast, resource-efficient, and accessible for resource-limited researchers.

Abstract

Efficient materials discovery requires reducing costly first-principles calculations for training machine-learned interatomic potentials (MLIPs). We develop an active learning (AL) framework that iteratively selects informative structures from the Materials Project and Open Quantum Materials Database (OQMD) using compositional and property-based descriptors with a neural network ensemble model. Query-by-Committee enables real-time uncertainty quantification. We compare four strategies: random sampling (baseline), uncertainty-based sampling, diversity-based sampling (k-means clustering with farthest-point refinement), and a hybrid approach. Experiments across four material systems (C, Si, Fe, and TiO2) with 5 random seeds demonstrate that diversity sampling achieves competitive or superior performance, with 10.9% improvement on TiO2. Our approach achieves equivalent accuracy with 5-13% fewer labeled samples than random baselines. The complete pipeline executes on Google Colab in under 4 hours per system using less than 8 GB RAM, democratizing MLIP development for resource-limited researchers. Open-source code and configurations are available on GitHub. This multi-system evaluation provides practical guidelines for data-efficient MLIP training and highlights integration with symmetry-aware architectures as a promising future direction.