Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions

TL;DR

Orbital Mixer introduces a basis-dependent approach to predict molecular electronic structures directly from atomic orbital features, achieving competitive accuracy with scalable architecture, advancing quantum chemistry machine learning methods.

Contribution

This work presents Orbital Mixer, a novel basis-dependent model that predicts molecular wavefunctions directly from atomic orbital features, differing from prior fixed-configuration property prediction models.

Findings

Achieves competitive accuracy in Hamiltonian and orbital energy predictions.

Uses MLP Mixer layers within a simple, scalable architecture.

Outperforms some existing models in electronic structure prediction.

Abstract

Leveraging ab initio data at scale has enabled the development of machine learning models capable of extremely accurate and fast molecular property prediction. A central paradigm of many previous works focuses on generating predictions for only a fixed set of properties. Recent lines of research instead aim to explicitly learn the electronic structure via molecular wavefunctions from which other quantum chemical properties can directly be derived. While previous methods generate predictions as a function of only the atomic configuration, in this work we present an alternate approach that directly purposes basis dependent information to predict molecular electronic structure. The backbone of our model, Orbital Mixer, uses MLP Mixer layers within a simple, intuitive, and scalable architecture and achieves competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies compared to the state-of-the-art.