Sparse feature selection via fast embedding spectral analysis

Jingyu Wang

doi:10.1016/j.patcog.2023.109472

Sparse feature selection via fast embedding spectral analysis

2023-07-01

10

PRE

AI

DOI：10.1016/j.patcog.2023.109472

Original

Original request for help

Save

Abstract

En 中文

Feature selection has been a research hotspot in many fields. Models based on graph learning are cur-rently the most popular approaches. However, the sparsity of most models is not strong, and graph learn-ing for pair-sample evaluation takes a lot of time. pound 2 , 1-norm regularization is the sparsity strategy adopted in most sparse models at present since the convex function is easy to solve. Nevertheless, the sparsity of pound 2 , 1-norm is insufficient, and there exist parameter adjustment problems. pound 2 , 0-norm is a better choice, which can strengthen the sparse constraints of the subspace. In this paper, the Sparse feature selection via Fast Embedding Spectral Analysis (SFESA) is proposed.Firstly, an adaptive anchor nearest neighbor graph is constructed to avoid the high time cost of learning pairwise nearest neighbor graphs to a certain extent. The low-dimensional embedding of data manifold structure is maintained by performing spectral analysis for the constructed graph. Secondly, the projected data is approximated to the low-dimensional embedding structure via a regularization term. Finally, pound 2 , 0 -norm is employed to constrain the projection matrix to enhance the subspace sparsity. Furthermore, a fast iterative algorithm is presented to solve this non-convex optimization problem. Extensive experi-ments on multiple public datasets show that SFESA can obtain excellent performance in less time.(c) 2023 Elsevier Ltd. All rights reserved.

Keywords:

Unsupervised learning

Feature selection

Spectral analysis

Sparse subspace

? 2 0-Norm

Sparse feature selection via fast embedding spectral analysis

Abstract

Journal

Organization