Adaptive graph-based generalized regression model for unsupervised feature selection

作者：

Highlights：

• A generalized regression model coupled with a novel uncorrelated constraint and adaptive graph structure learning is proposed to select discriminative and uncorrelated features.

• The similarity-induced graph matrix is adaptively learned in the reduced subspace.

• An efficient alternative optimization algorithm is developed.

摘要

•A generalized regression model coupled with a novel uncorrelated constraint and adaptive graph structure learning is proposed to select discriminative and uncorrelated features.•The similarity-induced graph matrix is adaptively learned in the reduced subspace.•An efficient alternative optimization algorithm is developed.

论文关键词：Unsupervised feature selection,Generalized regression model,Adaptive graph learning

论文评审过程：Received 22 December 2020, Revised 19 April 2021, Accepted 15 May 2021, Available online 26 May 2021, Version of Record 31 May 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107156