Improving Sample and Feature Selection with Principal Covariates Regression

TL;DR

This paper enhances feature and sample selection methods by integrating supervised information through Principal Covariates Regression, leading to improved model performance and efficiency in chemistry and materials science applications.

Contribution

It introduces PCov-CUR and PCov-FPS, modified selection schemes that incorporate target data, improving supervised task accuracy and reducing data requirements.

Findings

Supervised selection improves regression accuracy.

Significant reduction in features and samples needed.

Enhanced performance in chemistry and materials science applications.

Abstract

Selecting the most relevant features and samples out of a large set of candidates is a task that occurs very often in the context of automated data analysis, where it can be used to improve the computational performance, and also often the transferability, of a model. Here we focus on two popular sub-selection schemes which have been applied to this end: CUR decomposition, that is based on a low-rank approximation of the feature matrix and Farthest Point Sampling, that relies on the iterative identification of the most diverse samples and discriminating features. We modify these unsupervised approaches, incorporating a supervised component following the same spirit as the Principal Covariates Regression (PCovR) method. We show that incorporating target information provides selections that perform better in supervised tasks, which we demonstrate with ridge regression, kernel ridge regression, and sparse kernel regression. We also show that incorporating aspects of simple supervised learning models can improve the accuracy of more complex models, such as feed-forward neural networks. We present adjustments to minimize the impact that any subselection may incur when performing unsupervised tasks. We demonstrate the significant improvements associated with the use of PCov-CUR and PCov-FPS selections for applications to chemistry and materials science, typically reducing by a factor of two the number of features and samples which are required to achieve a given level of regression accuracy.