Designing Feature Vector Representations: A case study from Chemistry

TL;DR

This paper investigates various feature vector representations for chemical data, analyzing their similarities and differences to improve data reduction, comparison, and clustering in chemical multivariate ensemble analysis.

Contribution

It provides a comparative analysis of different feature representations, highlighting their similarities, differences, and potential for future development in chemical data analysis.

Findings

Partial confirmation of expected behavior in feature representations

Surprising observations about distance distributions and clustering tendencies

Insights for future development of chemical feature vectors

Abstract

We present a case study investigating feature descriptors in the context of the analysis of chemical multivariate ensemble data. The data of each ensemble member consists of three parts: the design parameters for each ensemble member, field data resulting from the numerical simulations, and physical properties of the molecules. Since feature-based methods have the potential to reduce the data complexity and facilitate comparison and clustering, we are focusing on such methods. However, there are many options to design the feature vector representation and there is no obvious preference. To get a better understanding of the different representations, we analyze their similarities and differences. Thereby, we focus on three characteristics derived from the representations: the distribution of pairwise distances, the clustering tendency, and the rank-order of the pairwise distances. The results of our investigations partially confirmed expected behavior, but also provided some surprising observations that can be used for the future development of feature representations in the chemical domain.