Learning molecular energies using localized graph kernels

Abstract

Recent machine learning methods make it possible to model potential energy of atomic configurations with chemical-level accuracy (as calculated from ab-initio calculations) and at speeds suitable for molecular dynam- ics simulation. Best performance is achieved when the known physical constraints are encoded in the machine learning models. For example, the atomic energy is invariant under global translations and rotations, it is also invariant to permutations of same-species atoms. Although simple to state, these symmetries are complicated to encode into machine learning algorithms. In this paper, we present a machine learning approach based on graph theory that naturally incorporates translation, rotation, and permutation symmetries. Specifically, we use a random walk graph kernel to measure the similarity of two adjacency matrices, each of which represents a local atomic environment. This Graph Approximated Energy (GRAPE) approach is flexible and admits many possible extensions. We benchmark a simple version of GRAPE by predicting atomization energies on a standard dataset of organic molecules.

References in corpus (2)

• Kernel methods in machine learning
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials

Cited by in corpus (22)

• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine learning a general purpose interatomic potential for silicon
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Hierarchical modeling of molecular energies using a deep neural network
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Applying machine learning techniques to predict the properties of energetic materials
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Efficient nonparametric $n$-body force fields from machine learning
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Graph Kernels: A Survey
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies
• Prediction of Atomization Energy Using Graph Kernel and Active Learning
• An Atomistic Fingerprint Algorithm for Learning Ab Initio Molecular Force Fields
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Understanding Isomorphism Bias in Graph Data Sets
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations