Open Source Infrastructure for Differentiable Density Functional Theory

TL;DR

This paper introduces an open source infrastructure for training neural exchange correlation functionals in quantum chemistry, standardizing the pipeline and integrating it into the DeepChem library to facilitate research in differentiable quantum chemistry methods.

Contribution

The authors develop and open source a standardized software platform for training neural exchange correlation functionals, advancing differentiable quantum chemistry research.

Findings

Open sourced the model in DeepChem library

Standardized processing pipeline for training functionals

Facilitates further research in differentiable quantum chemistry

Abstract

Learning exchange correlation functionals, used in quantum chemistry calculations, from data has become increasingly important in recent years, but training such a functional requires sophisticated software infrastructure. For this reason, we build open source infrastructure to train neural exchange correlation functionals. We aim to standardize the processing pipeline by adapting state-of-the-art techniques from work done by multiple groups. We have open sourced the model in the DeepChem library to provide a platform for additional research on differentiable quantum chemistry methods.