Symmetrical Graph Neural Network for Quantum Chemistry, with Dual R/K Space

TL;DR

This paper introduces a symmetry-aware graph neural network for quantum chemistry that incorporates molecular symmetry and dual space (real and momentum) information, improving property prediction and orbital distribution analysis.

Contribution

It presents a comprehensive symmetry-extended GNN model that captures orbital symmetries in both ground and excited states, addressing limitations of previous models.

Findings

Accurately predicts properties in real and momentum spaces.

Effectively predicts orbital distributions and active regions.

Demonstrates superior performance over existing models.

Abstract

Most of current neural network models in quantum chemistry (QC) exclude the molecular symmetry, separate the well-correlated real space (R space), and momenta space (K space) into two individuals, which lack the essential physics in molecular chemistry. In this work, by endorsing the molecular symmetry and elementals of group theory, we propose a comprehensive method to apply symmetry in the graph neural network (SY-GNN), which extends the property-predicting coverage to all the orbital symmetry for both ground and excited states. SY-GNN shows excellent performance in predicting both the absolute and relative of R and K spaces quantities. Besides the numerical properties, SY-GNN also can predict the orbitals distributions in real space, providing the active regions of chemical reactions. We believe the symmetry endorsed deep learning scheme covers the significant physics inside and is essential for the application of neural networks in QC and many other research fields in the future.