Edge Direction-invariant Graph Neural Networks for Molecular Dipole Moments Prediction

TL;DR

This paper introduces edge direction-invariant graph neural networks that effectively incorporate geometric information to predict molecular dipole moments with high accuracy, overcoming limitations of traditional topological graph embeddings.

Contribution

The paper proposes a novel embedding method for GNNs that directly encodes geometric and physical properties, improving dipole moment prediction accuracy.

Findings

Model achieves accuracy comparable to ab-initio calculations.

Effectively captures interatomic interactions in extended geometries.

Outperforms traditional topological graph methods.

Abstract

The dipole moment is a physical quantity indicating the polarity of a molecule and is determined by reflecting the electrical properties of constituent atoms and the geometric properties of the molecule. Most embeddings used to represent graph representations in traditional graph neural network methodologies treat molecules as topological graphs, creating a significant barrier to the goal of recognizing geometric information. Unlike existing embeddings dealing with equivariance, which have been proposed to handle the 3D structure of molecules properly, our proposed embeddings directly express the physical implications of the local contribution of dipole moments. We show that the developed model works reasonably even for molecules with extended geometries and captures more interatomic interaction information, significantly improving the prediction results with accuracy comparable to ab-initio calculations.