Directional Message Passing for Molecular Graphs

Abstract

Graph neural networks have recently achieved great successes in predicting quantum mechanical properties of molecules. These models represent a molecule as a graph using only the distance between atoms (nodes). They do not, however, consider the spatial direction from one atom to another, despite directional information playing a central role in empirical potentials for molecules, e.g. in angular potentials. To alleviate this limitation we propose directional message passing, in which we embed the messages passed between atoms instead of the atoms themselves. Each message is associated with a direction in coordinate space. These directional message embeddings are rotationally equivariant since the associated directions rotate with the molecule. We propose a message passing scheme analogous to belief propagation, which uses the directional information by transforming messages based on the angle between them. Additionally, we use spherical Bessel functions and spherical harmonics to construct theoretically well-founded, orthogonal representations that achieve better performance than the currently prevalent Gaussian radial basis representations while using fewer than 1/4 of the parameters. We leverage these innovations to construct the directional message passing neural network (DimeNet). DimeNet outperforms previous GNNs on average by 76% on MD17 and by 31% on QM9. Our implementation is available online.

Published as a conference paper at ICLR 2020. Author name changed from Johannes Klicpera to Johannes Gasteiger

Cited by in corpus (35)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• Inverse design of 3d molecular structures with conditional generative neural networks
• AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
• Toward Explainable AI for Regression Models
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquids
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Graph Neural Networks Accelerated Molecular Dynamics
• Graph neural networks for simulating crack coalescence and propagation in brittle materials
• Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
• Descriptors-free Collective Variables From Geometric Graph Neural Networks
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Boosting Heterogeneous Catalyst Discovery by Structurally Constrained Deep Learning Models
• Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials
• No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
• A smooth basis for atomistic machine learning
• PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction
• Scaling Graph Neural Networks to Large Proteins
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model