Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules

Abstract

Many important tasks in chemistry revolve around molecules during reactions. This requires predictions far from the equilibrium, while most recent work in machine learning for molecules has been focused on equilibrium or near-equilibrium states. In this paper we aim to extend this scope in three ways. First, we propose the DimeNet++ model, which is 8x faster and 10% more accurate than the original DimeNet on the QM9 benchmark of equilibrium molecules. Second, we validate DimeNet++ on highly reactive molecules by developing the challenging COLL dataset, which contains distorted configurations of small molecules during collisions. Finally, we investigate ensembling and mean-variance estimation for uncertainty quantification with the goal of accelerating the exploration of the vast space of non-equilibrium structures. Our DimeNet++ implementation as well as the COLL dataset are available online.

Published at the Machine Learning for Molecules Workshop at NeurIPS 2020. Author name changed from Johannes Klicpera to Johannes Gasteiger

Cited by in corpus (15)

• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• DPA-2: a large atomic model as a multi-task learner
• AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Graph Neural Networks Accelerated Molecular Dynamics
• High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO
• Implementing graph neural networks with TensorFlow-Keras
• Modeling electronic response properties with an explicit-electron machine learning potential
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Enhanced Sampling for Free Energy Profiles with Post-Transition-State Bifurcations
• Coherent energy and force uncertainty in deep learning force fields
• Neural Polarization: Toward Electron Density for Molecules by Extending Equivariant Networks