Efficient training of generative models from multireference simulations and its application to the design of Dy complexes with large magnetic anisotropy

TL;DR

This paper introduces a semi-supervised training method for generative models that drastically reduces data requirements from multireference simulations, enabling the design of Dy complexes with high magnetic anisotropy.

Contribution

The authors develop a chemically-inspired, semi-supervised training approach for variational autoencoders that cuts multireference simulation costs by 100-fold, facilitating complex molecule generation.

Findings

Generated hundreds of new Dy complexes with record magnetic anisotropy

Achieved effective model training with datasets as small as 1,000 multireference calculations

Demonstrated the potential for computational design of complex coordination compounds

Abstract

Generative machine learning models can potentially provide direct access to novel and relevant portions of the full chemical space, overcoming the cost of systematic sampling. However, the training of these models generally requires a large amount of data, often precluding the use of expensive high-level ab initio simulations for this task. The generation of coordination compounds of Dy with large magnetic anisotropy represents a topical example, where multireference simulations of large molecules are necessary to perform reliable predictions. Here, we show that a semi-supervised chemically-inspired training-by-proxy of generative variational autoencoders can reduce the cost associated with building a training set from multireference simulations by two orders of magnitude. We illustrate the power of this approach by generating 100s of new organic ligands for Dy(III) pentagonal bipyramidal complexes exhibiting record values of magnetic anisotropy, while starting from datasets as small as 1k multireference calculations. This work thus paves the way to the computational generation of molecules as complex coordination compounds with target electronic and magnetic properties.