Representing spherical tensors with scalar-based machine-learning models

Abstract

Rotational symmetry plays a central role in physics, providing an elegant framework to describe how the properties of 3D objects -- from atoms to the macroscopic scale -- transform under the action of rigid rotations. Equivariant models of 3D point clouds are able to approximate structure-property relations in a way that is fully consistent with the structure of the rotation group, by combining intermediate representations that are themselves spherical tensors. The symmetry constraints however make this approach computationally demanding and cumbersome to implement, which motivates increasingly popular unconstrained architectures that learn approximate symmetries as part of the training process. In this work, we explore a third route to tackle this learning problem, where equivariant functions are expressed as the product of a scalar function of the point cloud coordinates and a small basis of tensors with the appropriate symmetry. We also propose approximations of the general expressions that, while lacking universal approximation properties, are fast, simple to implement, and accurate in practical settings.

References in corpus (26)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine Learning Unifies the Modelling of Materials and Molecules
• Competing quantum effects in the dynamics of a flexible water model
• Physics-inspired structural representations for molecules and materials
• Materials Cloud, a platform for open computational science
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• i-PI: A Python interface for ab initio path integral molecular dynamics simulations
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• On the Consistency of Approximate Quantum Dynamics Simulation Methods for Vibrational Spectra in the Condensed Phase
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• Predicting tensorial molecular properties with equivariant machine-learning models
• Differentiable quantum chemistry with PySCF for molecules and materials at the mean-field level and beyond
• A spectral-neighbour representation for vector fields: machine-learning potentials including spin
• Completeness of Atomic Structure Representations
• Dynamical Heterogeneity in Supercooled Water and its Spectroscopic Fingerprints
• A general formalism for machine-learning models based on multipolar-spherical harmonics