AtomSets -- A Hierarchical Transfer Learning Framework for Small and Large Materials Datasets

TL;DR

AtomSets is a hierarchical transfer learning framework that achieves high accuracy in predicting materials properties across small and large datasets, outperforming existing models and requiring minimal domain knowledge.

Contribution

The paper introduces AtomSets, a novel transfer learning framework using graph networks that maintains high accuracy across varying dataset sizes in materials science.

Findings

AtomSets outperforms state-of-the-art models on small and large datasets.

AtomSets achieves lower errors than classical machine learning models.

AtomSets demonstrates better transferability in materials discovery simulations.

Abstract

Predicting materials properties from composition or structure is of great interest to the materials science community. Deep learning has recently garnered considerable interest in materials predictive tasks with low model errors when dealing with large materials data. However, deep learning models suffer in the small data regime that is common in materials science. Here we leverage the transfer learning concept and the graph network deep learning framework and develop the AtomSets machine learning framework for consistent high model accuracy at both small and large materials data. The AtomSets models can work with both compositional and structural materials data. By combining with transfer learned features from graph networks, they can achieve state-of-the-art accuracy from using small compositional data (<400) to large structural data (>130,000). The AtomSets models show much lower errors than the state-of-the-art graph network models at small data limits and the classical machine learning models at large data limits. They also transfer better in the simulated materials discovery process where the targeted materials have property values out of the training data limits. The models require minimal domain knowledge inputs and are free from feature engineering. The presented AtomSets model framework opens new routes for machine learning-assisted materials design and discovery.