Unified theory of atom-centered representations and message-passing machine-learning schemes

Abstract

Data-driven schemes that associate molecular and crystal structures with their microscopic properties share the need for a concise, effective description of the arrangement of their atomic constituents. Many types of models rely on descriptions of atom-centered environments, that are associated with an atomic property or with an atomic contribution to an extensive macroscopic quantity. Frameworks in this class can be understood in terms of atom-centered density correlations (ACDC), that are used as a basis for a body-ordered, symmetry-adapted expansion of the targets. Several other schemes, that gather information on the relationship between neighboring atoms using "message-passing" ideas, cannot be directly mapped to correlations centered around a single atom. We generalize the ACDC framework to include multi-centered information, generating representations that provide a complete linear basis to regress symmetric functions of atomic coordinates, and provides a coherent foundation to systematize our understanding of both atom-centered and message-passing, invariant and equivariant machine-learning schemes.

References in corpus (27)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Physics-inspired structural representations for molecules and materials
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Incorporating long-range physics in atomic-scale machine learning
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Efficient nonparametric $n$-body force fields from machine learning
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Optimal radial basis for density-based atomic representations
• Unified theory of atom-centered representations and message-passing machine-learning schemes

Cited by in corpus (1)

• Unified theory of atom-centered representations and message-passing machine-learning schemes