Predicting tensorial molecular properties with equivariant machine-learning models

TL;DR

This paper introduces a scalable equivariant machine-learning model that effectively predicts tensorial molecular properties by embedding molecular symmetries, demonstrating its potential in materials modeling.

Contribution

The authors develop a novel equivariant machine-learning framework capable of accurately predicting tensorial molecular properties, extending symmetry embedding strategies beyond scalar quantities.

Findings

Accurate predictions for dielectric tensorial properties.

Effective modeling of magnetic tensorial properties.

Demonstrated scalability across various molecules.

Abstract

Embedding molecular symmetries into machine-learning models is key for efficient learning of chemico-physical scalar properties, but little evidence on how to extend the same strategy to tensorial quantities exists. Here we formulate a scalable equivariant machine-learning model based on local atomic environment descriptors. We apply it to a series of molecules and show that accurate predictions can be achieved for a comprehensive list of dielectric and magnetic tensorial properties of different ranks. These results show that equivariant models are a promising platform to extend the scope of machine learning in materials modelling.