Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality

Abstract

Recent advances in machine-learned interatomic potentials largely benefit from the atomistic representation and locally invariant many-body descriptors. It was however recently argued that including three- (or even four-) body features is incomplete to distinguish specific local structures. Utilizing an embedded density descriptor made by linear combinations of neighboring atomic orbitals and realizing that each orbital coefficient physically depends on its own local environment, we propose a recursively embedded atom neural network model. We formally prove that this model can efficiently incorporate complete many-body correlations without explicitly computing high-order terms. This model not only successfully addresses challenges regarding local completeness and nonlocality in representative systems, but also provides an easy and general way to update local many-body descriptors to have a message-passing form without changing their basic structures.

arXiv commentThis work has been published in Phys. Rev. Lett

References in corpus (25)

• Decoupled Weight Decay Regularization
• 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
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• 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
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning for electronically excited states of molecules
• Ab initio thermodynamics of liquid and solid water
• Alchemical and structural distribution based representation for improved QML
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Machine learning enables long time scale molecular photodynamics simulations
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Conceptual and practical bases for the high accuracy of machine learning interatomic potential
• Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
• Accelerating Atomistic Simulations with Piecewise Machine Learned Ab Initio Potentials at Classical Force Field-like Cost
• A practical approach to Hohenberg-Kohn maps based on many-body correlations: learning the electronic density

Cited by in corpus (11)

• 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
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• A Machine Learning Approach Based on Range Corrected Deep Potential Model for Efficient Vibrational Frequency Computation
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems