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

📅 2026-01-11
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work proposes an active learning framework to reduce the cost of first-principles calculations required for training machine learning interatomic potentials (MLIPs). By integrating compositional and property-based descriptors, the approach employs neural network ensembles with Query-by-Committee to quantify predictive uncertainty. The study systematically evaluates sampling strategies—including diversity-based methods (k-means and farthest point sampling), uncertainty-based selection, and hybrid approaches—across multiple material systems such as carbon, silicon, iron, and titanium oxides. For the first time in multi-material settings, diversity sampling is shown to significantly outperform alternatives, achieving target accuracy with 5–13% fewer labeled samples on average; notably, it yields a 10.9% performance gain for titanium oxides (p = 0.008). The entire workflow completes within four hours on a standard Google Colab instance with 8 GB memory.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

active learning
machine-learned interatomic potentials
data efficiency
materials discovery
first-principles calculations
Innovation

Methods, ideas, or system contributions that make the work stand out.

active learning
machine-learned interatomic potentials
diversity sampling
uncertainty quantification
data-efficient ML
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
M
Mohammed Azeez Khan
Department of Computer Science and Engineering, NIT Warangal, India
A
Aaron D'Souza
Department of Electronics and Communication Engineering, NIT Warangal, India
V
Vijay Choyal
Department of Mechanical Engineering, NIT Warangal, India