A Bin and Hash Method for Analyzing Reference Data and Descriptors in Machine Learning Potentials

TL;DR

This paper introduces the bin-and-hash (BAH) algorithm, a novel method to efficiently analyze and compare large multidimensional datasets in machine learning potentials, improving data handling and quality assessment.

Contribution

The BAH algorithm provides a general, efficient approach for identifying and comparing large sets of vectors in ML potentials, aiding in data reduction and quality control.

Findings

Enables efficient comparison of large multidimensional vectors

Reduces redundancy in reference datasets

Improves assessment of descriptor quality

Abstract

In recent years the development of machine learning (ML) potentials (MLP) has become a very active field of research. Numerous approaches have been proposed, which allow to perform extended simulations of large systems at a small fraction of the computational costs of electronic structure calculations. The key to the success of modern ML potentials is the close-to first principles quality description of the atomic interactions. This accuracy is reached by using very flexible functional forms in combination with high-level reference data from electronic structure calculations. These data sets can include up to hundreds of thousands of structures covering millions of atomic environments to ensure that all relevant features of the potential energy surface are well represented. The handling of such large data sets is nowadays becoming one of the main challenges in the construction of ML potentials. In this paper we present a method, the bin-and-hash (BAH) algorithm, to overcome this problem by enabling the efficient identification and comparison of large numbers of multidimensional vectors. Such vectors emerge in multiple contexts in the construction of ML potentials. Examples are the comparison of local atomic environments to identify and avoid unnecessary redundant information in the reference data sets that is costly in terms of both the electronic structure calculations as well as the training process, the assessment of the quality of the descriptors used as structural fingerprints in many types of ML potentials, and the detection of possibly unreliable data points. The BAH algorithm is illustrated for the example of high-dimensional neural network potentials using atom-centered symmetry functions for the geometrical description of the atomic environments, but the method is general and can be combined with any current type of ML potential.