Fast Uncertainty Estimates in Deep Learning Interatomic Potentials

Abstract

Deep learning has emerged as a promising paradigm to give access to highly accurate predictions of molecular and materials properties. A common short-coming shared by current approaches, however, is that neural networks only give point estimates of their predictions and do not come with predictive uncertainties associated with these estimates. Existing uncertainty quantification efforts have primarily leveraged the standard deviation of predictions across an ensemble of independently trained neural networks. This incurs a large computational overhead in both training and prediction that often results in order-of-magnitude more expensive predictions. Here, we propose a method to estimate the predictive uncertainty based on a single neural network without the need for an ensemble. This allows us to obtain uncertainty estimates with virtually no additional computational overhead over standard training and inference. We demonstrate that the quality of the uncertainty estimates matches those obtained from deep ensembles. We further examine the uncertainty estimates of our methods and deep ensembles across the configuration space of our test system and compare the uncertainties to the potential energy surface. Finally, we study the efficacy of the method in an active learning setting and find the results to match an ensemble-based strategy at order-of-magnitude reduced computational cost.

References in corpus (3)

• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Micron-scale heterogeneous catalysis with Bayesian force fields from first principles and active learning

Cited by in corpus (15)

• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Accurate machine learning force fields via experimental and simulation data fusion
• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Prediction rigidities for data-driven chemistry
• Enhanced sampling of robust molecular datasets with uncertainty-based collective variables
• Efficient ensemble uncertainty estimation in Gaussian Processes Regression
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• Multi-head committees enable direct uncertainty prediction for atomistic foundation models
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Accurate Machine Learning Interatomic Potentials for Polyacene Molecular Crystals: Application to Single Molecule Host-Guest Systems
• Comparing the latent features of universal machine-learning interatomic potentials
• A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning