Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders
This method offers a more computationally and energy-efficient solution for feature selection, which is particularly beneficial for devices with limited resources.
This paper proposes QuickSelection, a novel unsupervised feature selection method that leverages the strength of neurons in sparsely connected denoising autoencoders. QuickSelection achieves the best trade-off in classification and clustering accuracy, running time, and memory usage across several benchmark datasets, while also requiring the least energy among state-of-the-art autoencoder-based methods.
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.