Recursive evaluation and iterative contraction of $N$-body equivariant features

Abstract

Mapping an atomistic configuration to an $N$-point correlation of a field associated with the atomic positions (e.g. an atomic density) has emerged as an elegant and effective solution to represent structures as the input of machine-learning algorithms. While it has become clear that low-order density correlations do not provide a complete representation of an atomic environment, the exponential increase in the number of possible $N$-body invariants makes it difficult to design a concise and effective representation. We discuss how to exploit recursion relations between equivariant features of different orders (generalizations of $N$-body invariants that provide a complete representation of the symmetries of improper rotations) to compute high-order terms efficiently. In combination with the automatic selection of the most expressive combination of features at each order, this approach provides a conceptual and practical framework to generate systematically-improvable, symmetry adapted representations for atomistic machine learning.

References in corpus (32)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• 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
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning prediction errors better than DFT accuracy
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• A Transferable Machine-Learning Model of the Electron Density
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Incorporating long-range physics in atomic-scale machine learning
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Atom-Density Representations for Machine Learning
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Efficient nonparametric $n$-body force fields from machine learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• A sparse representation for potential energy surface
• Learning molecular energies using localized graph kernels
• A Bayesian approach to NMR crystal structure determination

Cited by in corpus (38)

• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Physics-inspired structural representations for molecules and materials
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• A complete description of thermodynamic stabilities of molecular crystals
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
• Efficient implementation of atom-density representations
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Tensor-reduced atomic density representations
• Completeness of Atomic Structure Representations
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• 3DReact: Geometric deep learning for chemical reactions
• Optimal radial basis for density-based atomic representations
• Kernel based quantum machine learning at record rate : Many-body distribution functionals as compact representations
• SPA${}^{\mathrm{H}}$M: the Spectrum of Approximated Hamiltonian Matrices representations
• Mean-Field Density Matrix Decompositions
• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• A smooth basis for atomistic machine learning
• Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Relevant, hidden, and frustrated information in high-dimensional analyses of complex dynamical systems with internal noise
• A data driven approach to classify descriptors based on their efficiency in translating noisy trajectories into physically-relevant information
• Efficient Long-Range Convolutions for Point Clouds
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Representing spherical tensors with scalar-based machine-learning models
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Learning electron densities in the condensed phase
• Integer linear programming for unsupervised training set selection in molecular machine learning
• Compressing local atomic neighbourhood descriptors
• Machine learning of electronic structure and atomistic properties from the external potential
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems