Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

TL;DR

This paper introduces QuickSelection, a fast, energy-efficient, sparse autoencoder-based method for unsupervised feature selection that outperforms existing techniques in accuracy, speed, and memory usage on various datasets.

Contribution

The paper proposes a novel sparse autoencoder approach using neuron strength for feature importance, significantly improving efficiency and energy consumption in feature selection.

Findings

Achieves the best trade-off between accuracy, speed, and memory on benchmark datasets.

Requires the least energy compared to state-of-the-art autoencoder methods.

Operates in a purely sparse manner, enhancing computational efficiency.

Abstract

Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a dataset, has been introduced as a solution to this problem. Most of the existing feature selection methods are computationally inefficient; inefficient algorithms lead to high energy consumption, which is not desirable for devices with limited computational and energy resources. In this paper, a novel and flexible method for unsupervised feature selection is proposed. This method, named QuickSelection, introduces the strength of the neuron in sparse neural networks as a criterion to measure the feature importance. This criterion, blended with sparsely connected denoising autoencoders trained with the sparse evolutionary training procedure, derives the importance of all input features simultaneously. We implement QuickSelection in a purely sparse manner as opposed to the typical approach of using a binary mask over connections to simulate sparsity. It results in a considerable speed increase and memory reduction. When tested on several benchmark datasets, including five low-dimensional and three high-dimensional datasets, the proposed method is able to achieve the best trade-off of classification and clustering accuracy, running time, and maximum memory usage, among widely used approaches for feature selection. Besides, our proposed method requires the least amount of energy among the state-of-the-art autoencoder-based feature selection methods.