ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations

Abstract

With massive amounts of atomic simulation data available, there is a huge opportunity to develop fast and accurate machine learning models to approximate expensive physics-based calculations. The key quantity to estimate is atomic forces, where the state-of-the-art Graph Neural Networks (GNNs) explicitly enforce basic physical constraints such as rotation-covariance. However, to strictly satisfy the physical constraints, existing models have to make tradeoffs between computational efficiency and model expressiveness. Here we explore an alternative approach. By not imposing explicit physical constraints, we can flexibly design expressive models while maintaining their computational efficiency. Physical constraints are implicitly imposed by training the models using physics-based data augmentation. To evaluate the approach, we carefully design a scalable and expressive GNN model, ForceNet, and apply it to OC20 (Chanussot et al., 2020), an unprecedentedly-large dataset of quantum physics calculations. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs while being faster both in training and inference. Overall, our promising and counter-intuitive results open up an exciting avenue for future research.

References in corpus (17)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Searching for Activation Functions
• Interaction Networks for Learning about Objects, Relations and Physics
• Inelastic transport theory from first-principles: methodology and applications for nanoscale devices
• Learning to Simulate Complex Physics with Graph Networks
• A local Bayesian optimizer for atomic structures
• PubChemQC PM6: A dataset of 221 million molecules with optimized molecular geometries and electronic properties
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage

Cited by in corpus (8)

• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Graph Neural Networks Accelerated Molecular Dynamics
• Thermodynamics-informed graph neural networks
• Rotation Invariant Graph Neural Networks using Spin Convolutions
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• Frame Averaging for Invariant and Equivariant Network Design
• Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks