Subspace learning for unsupervised feature selection via matrix factorization

作者：

Highlights：

• Propose a new feature selection based on matrix factorization.

• Present a fast convergent algorithm for matrix factorization on certain constraints.

• Incorporate kernel tricks into feature selection problems.

• Construct a unified framework for feature extraction, feature selection and clustering.

摘要

Highlights•Propose a new feature selection based on matrix factorization.•Present a fast convergent algorithm for matrix factorization on certain constraints.•Incorporate kernel tricks into feature selection problems.•Construct a unified framework for feature extraction, feature selection and clustering.

论文关键词：Machine learning,Feature selection,Unsupervised learning,Matrix factorization,Subspace distance,Kernel method

论文评审过程：Received 20 December 2013, Revised 28 July 2014, Accepted 6 August 2014, Available online 15 August 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.08.004