Machine learning of molecular properties: locality and active learning

Abstract

In recent years the machine learning techniques have shown a great potential in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy comparable to that of DFT on another hand make machine learning algorithms efficient for high-throughput screening through chemical and configurational space. However, the machine learning algorithms available in the literature require large training datasets to reach the chemical accuracy and also show large errors for the so-called outliers - the out-of-sample molecules, not well-represented in the training set. In the present paper we propose a new machine learning algorithm for predicting molecular properties that addresses these two issues: it is based on a local model of interatomic interactions providing high accuracy when trained on relatively small training sets and an active learning algorithm of optimally choosing the training set that significantly reduces the errors for the outliers. We compare our model to the other state-of-the-art algorithms from the literature on the widely used benchmark tests.

revised version

References in corpus (2)

• Hierarchical modeling of molecular energies using a deep neural network
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity

Cited by in corpus (42)

• On-the-fly machine learning force field generation: Application to melting points
• Machine learning a general purpose interatomic potential for silicon
• FCHL revisited: faster and more accurate quantum machine learning
• A Transferable Machine-Learning Model of the Electron Density
• Exploring Phononic Properties of Two-Dimensional Materials using Machine Learning Interatomic Potentials
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Automated discovery of a robust interatomic potential for aluminum
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Global optimization of atomistic structure enhanced by machine learning
• Modular machine learning-based elastoplasticity: generalization in the context of limited data
• Equation of state of fluid methane from first principles with machine learning potentials
• Gaussian Process-Based Refinement of Dispersion Corrections
• Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction
• Machine learning configuration interaction for ab initio potential energy curves
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Automated Calculation of Thermal Rate Coefficients using Ring Polymer Molecular Dynamics and Machine-Learning Interatomic Potentials with Active Learning
• Transfer learning for chemically accurate interatomic neural network potentials
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Prediction of Atomization Energy Using Graph Kernel and Active Learning
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Moments
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• In operando active learning of interatomic interaction during large-scale simulations
• Lattice dynamics and elastic properties of alpha-U at high-temperature and high-pressure by machine learning potential simulations
• Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
• Atomistic modeling of bulk and grain boundary diffusion in solid electrolyte Li${}_6$PS${}_5$Cl using machine-learning interatomic potentials
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Fitting to magnetic forces improves the reliability of magnetic Moment Tensor Potentials
• AI-accelerated Materials Informatics Method for the Discovery of Ductile Alloys
• Machine Learning Framework for Modeling Exciton-Polaritons in Molecular Materials
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• Distributed Out-of-Memory NMF on CPU/GPU Architectures
• Surrogate-Based Black-Box Optimization Method for Costly Molecular Properties
• Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• HOAX: A Hyperparameter Optimization Algorithm Explorer for Neural Networks
• Integer linear programming for unsupervised training set selection in molecular machine learning