Generalization of Graph-Based Active Learning Relaxation Strategies Across Materials

TL;DR

This paper demonstrates that Finetuna, an active learning framework utilizing pretrained graph neural networks, can significantly reduce the number of DFT calculations needed for material relaxation, especially in out-of-domain systems.

Contribution

The study extends Finetuna's application to diverse materials, showing its effectiveness in reducing computational costs across various complex systems.

Findings

Reduces DFT calculations by up to 80% for alcohols and 3D structures.

Achieves 42% reduction for oxide systems.

Effective in out-of-domain material relaxations.

Abstract

Although density functional theory (DFT) has aided in accelerating the discovery of new materials, such calculations are computationally expensive, especially for high-throughput efforts. This has prompted an explosion in exploration of machine learning assisted techniques to improve the computational efficiency of DFT. In this study, we present a comprehensive investigation of the broader application of Finetuna, an active learning framework to accelerate structural relaxation in DFT with prior information from Open Catalyst Project pretrained graph neural networks. We explore the challenges associated with out-of-domain systems: alcohol ($C_{>2}$) on metal surfaces as larger adsorbates, metal-oxides with spin polarization, and three-dimensional (3D) structures like zeolites and metal-organic-frameworks. By pre-training machine learning models on large datasets and fine-tuning the model along the simulation, we demonstrate the framework's ability to conduct relaxations with fewer DFT calculations. Depending on the similarity of the test systems to the training systems, a more conservative querying strategy is applied. Our best-performing Finetuna strategy reduces the number of DFT single-point calculations by 80% for alcohols and 3D structures, and 42% for oxide systems.