Leveraging Composition-Based Material Descriptors for Machine Learning Optimization

TL;DR

This paper proposes strategies to reduce the number of composition-based descriptors needed for material classification, improving efficiency in machine learning models for materials like superconductors.

Contribution

It introduces a multi-objective optimization method for selecting minimal descriptor sets and evaluates strategies for descriptor invariance in material classification.

Findings

Multi-objective optimization effectively reduces descriptor sets.

Descriptor invariance testing aids in feature selection.

Strategies improve classification efficiency for superconductors.

Abstract

In this study, we evaluate several classifiers and focus on selecting a minimal set of appropriate material features. Our objective is to propose and discuss general strategies for reducing the number of descriptors required for material classification. The first strategy involves testing whether the critical temperature of the target material property is invariant with respect to binary groups of composition-based features. We also propose a multi-objective optimization procedure to reduce the set of composition-based material descriptors. The latter procedure is found to be particularly useful when applied to Bayesian classifiers. We test the proposed strategies focusing on low-temperature superconductors material data extracted from a public database.