# Deep Feature Selection using a Teacher-Student Network

## TL;DR

This paper introduces a novel teacher-student neural network approach for feature selection that improves classification and clustering accuracy while reducing model complexity in high-dimensional data.

## Contribution

It is the first to employ a teacher-student scheme specifically for feature selection, applicable to both supervised and unsupervised scenarios.

## Key findings

- Outperforms existing feature selection methods in accuracy.
- Demonstrates robustness to parameter variations.
- Reduces reconstruction error effectively.

## Abstract

High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the model. In this paper, we present a novel teacher-student feature selection (TSFS) method in which a 'teacher' (a deep neural network or a complicated dimension reduction method) is first employed to learn the best representation of data in low dimension. Then a 'student' network (a simple neural network) is used to perform feature selection by minimizing the reconstruction error of low dimensional representation. Although the teacher-student scheme is not new, to the best of our knowledge, it is the first time that this scheme is employed for feature selection. The proposed TSFS can be used for both supervised and unsupervised feature selection. This method is evaluated on different datasets and is compared with state-of-the-art existing feature selection methods. The results show that TSFS performs better in terms of classification and clustering accuracies and reconstruction error. Moreover, experimental evaluations demonstrate a low degree of sensitivity to parameter selection in the proposed method.