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

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.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Spectral Networks and Locally Connected Networks on Graphs
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• Machine learning prediction errors better than DFT accuracy

Cited by in corpus (15)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Message-passing neural networks for high-throughput polymer screening
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Rotation Invariant Graph Neural Networks using Spin Convolutions
• Hierarchical Inter-Message Passing for Learning on Molecular Graphs
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage
• Materials property prediction using symmetry-labeled graphs as atomic-position independent descriptors
• Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
• Molecule Property Prediction and Classification with Graph Hypernetworks
• Atomistic Graph Neural Networks for metals: Application to bcc iron
• Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective
• Predicting Kovats Retention Indices Using Graph Neural Networks
• Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks
• Analysis of Atomistic Representations Using Weighted Skip-Connections