Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials

TL;DR

This paper introduces an enhanced neural message passing model with edge updates for predicting molecular and material properties, demonstrating superior accuracy across multiple datasets and exploring optimal graph construction methods.

Contribution

The paper proposes a novel edge update mechanism in neural message passing models, improving property prediction accuracy for molecules and materials.

Findings

Edge update network improves prediction accuracy.

K-nearest neighbors graph construction outperforms other methods.

Model achieves state-of-the-art results on three datasets.

Abstract

Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials. In this work we extend the neural message passing model with an edge update network which allows the information exchanged between atoms to depend on the hidden state of the receiving atom. We benchmark the proposed model on three publicly available datasets (QM9, The Materials Project and OQMD) and show that the proposed model yields superior prediction of formation energies and other properties on all three datasets in comparison with the best published results. Furthermore we investigate different methods for constructing the graph used to represent crystalline structures and we find that using a graph based on K-nearest neighbors achieves better prediction accuracy than using maximum distance cutoff or the Voronoi tessellation graph.