Robustness of Local Predictions in Atomistic Machine Learning Models

Abstract

Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven simulations with a linear-scaling cost, and also allow for the identification and post-hoc interpretation of contributions from individual chemical environments and motifs to complicated macroscopic properties. However, even though there exist practical justifications for these decompositions, only the global quantity is rigorously defined, and thus it is unclear to what extent the atomistic terms predicted by the model can be trusted. Here, we introduce a quantitative metric, which we call the local prediction rigidity (LPR), that allows one to assess how robust the locally decomposed predictions of ML models are. We investigate the dependence of LPR on the aspects of model training, particularly the composition of training dataset, for a range of different problems from simple toy models to real chemical systems. We present strategies to systematically enhance the LPR, which can be used to improve the robustness, interpretability, and transferability of atomistic ML models.

References in corpus (25)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• 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
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine-learning based interatomic potential for amorphous carbon
• Nearsightedness of Electronic Matter
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Machine learning a general purpose interatomic potential for silicon
• Materials Cloud, a platform for open computational science
• A neural network interatomic potential for the phase change material GeTe
• Plane-wave based electronic structure calculations for correlated materials using dynamical mean-field theory and projected local orbitals
• Data-driven learning of total and local energies in elemental boron
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Learning the electronic density of states in condensed matter
• Machine learning driven simulated deposition of carbon films: from low-density to diamondlike amorphous carbon
• Heat transport in liquid water from first-principles and deep-neural-network simulations
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• Temperature- and vacancy-concentration-dependence of heat transport in Li${}_3$ClO from multi-method numerical simulations
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Exploring the configurational space of amorphous graphene with machine-learned atomic energies
• Heat flux for semi-local machine-learning potentials
• Predicting hot-electron free energies from ground-state data

Cited by in corpus (10)

• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Thermal conductivity of Li${}_3$PS${}_4$ solid electrolytes with ab initio accuracy
• Prediction rigidities for data-driven chemistry
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Uncertainty Quantification in Atomistic Simulations of Silicon using Interatomic Potentials
• Adaptive energy reference for machine-learning models of the electronic density of states
• Interpolating many-body wave functions for accelerated molecular dynamics on the near-exact electronic surface
• Shifting sands of hardware and software in exascale quantum mechanical simulations
• Assessing zero-shot generalisation behaviour in graph-neural-network interatomic potentials