Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory

Abstract

An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.

v2.0

References in corpus (11)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• An Accurate and Transferable Machine Learning Potential for Carbon
• On the redundancy in large material datasets: efficient and robust learning with less data
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances
• Vibrational entropy of crystalline solids from covariance of atomic displacements

Cited by in corpus (6)

• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Pre-training, fine-tuning, and distillation (PFD): Automatically generating machine learning force fields from universal models
• Multi-head committees enable direct uncertainty prediction for atomistic foundation models
• Topological descriptors for the electron density of inorganic solids
• A Generative Diffusion Model for Amorphous Materials
• Inverse design of bespoke interatomic potentials via active learning by information-matching