Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials (2018-06-01T00:00:00.000000Z)

TL;DR

This work extends 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.

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.

Authors

P. B. Jørgensen

3 papers

K. Jacobsen

2 papers

Mikkel N. Schmidt

2 papers

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

TL;DR

Abstract

Authors

References26 items

SchNet - A deep learning architecture for molecules and materials.

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.

Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Neural Message Passing for Quantum Chemistry

Interaction Networks for Learning about Objects, Relations and Physics

Quantum-chemical insights from deep tensor neural networks

Molecular graph convolutions: moving beyond fingerprints

The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies

Deep Residual Learning for Image Recognition

Gated Graph Sequence Neural Networks

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

Adam: A Method for Stochastic Optimization

Quantum chemistry structures and properties of 134 kilo molecules

Spectral Networks and Locally Connected Networks on Graphs

Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation

Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17

Fast and accurate modeling of molecular atomization energies with machine learning.

Extended-Connectivity Fingerprints

VORO++: a three-dimensional voronoi cell library in C++.

A new model for learning in graph domains

The inorganic crystal structure data base

The Graph Neural Network Model

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names