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

By Peter Bjørn Jørgensen, Karsten Wedel Jacobsen, Mikkel N. Schmidt. 2018

86 citations recorded by the source corpus.

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.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Graph Learning, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Shyue Ping Ong
2. Chi Chen
3. Abhishek Das
4. Brandon Wood
5. Stephan Günnemann
6. Johannes Klicpera
7. Jian Tang
8. Payel Das

In Materials Chemistry

1. Chi Chen
2. Shyue Ping Ong
3. Stephan Günnemann
4. Abhishek Das
5. Brandon Wood
6. Johannes Klicpera
7. Jian Tang
8. Payel Das

In Graph Learning

1. Stephan Günnemann
2. Chi Chen
3. Shyue Ping Ong
4. Johannes Klicpera
5. Jian Tang
6. Abhishek Das
7. Brandon Wood
8. Zuobai Zhang

In Computational Chemistry & Drug Discovery

1. Shyue Ping Ong
2. Chi Chen
3. Abhishek Das
4. Brandon Wood
5. Stephan Günnemann
6. Johannes Klicpera
7. Jian Tang
8. Janek Groß

Citations in the corpus

• Directional Message Passing for Molecular Graphs (2020, methodology): “(Undirected) edge embeddings have already been used in previous GNNs for molecules (Jørgensen et al., 2018; Chen et al., 2019a).”
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals (2018, background): “Gilmer et al. 37 later proposed the message passing neural network (MPNN) framework that includes the existing graph models with differences only in their update functions.”
• Protein Representation Learning by Geometric Structure Pretraining (2022, methodology): “Specifically, existing methods employed node/atom message passing (Gilmer et al., 2017; Schütt et al., 2017a;b), edge/bond message passing (Jørgensen et al., 2018; Chen et al., 2019) and directional information (Klicpera et al., 2020; Liu et al., 2021; Klicpera et al., 2021) to encode 2D or 3D…”
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage (2020, methodology): “information used in message passing [36].”