Ordinal preserving matrix factorization for unsupervised feature selection

作者：

Highlights：

•

• Ordinal Preserving Matrix Factorization (OPMF) is proposed for feature selection.

• OPMF incorporates ordinal structure and inner-product term into matrix factorization.

• An iterative updating algorithm is derived to solve the proposed OPMF algorithm.

摘要

•Ordinal Preserving Matrix Factorization (OPMF) is proposed for feature selection.•OPMF incorporates ordinal structure and inner-product term into matrix factorization.•An iterative updating algorithm is derived to solve the proposed OPMF algorithm.

论文关键词：Unsupervised feature selection,Matrix factorization,Ordinal locality structure preserving,Sparsity and low redundancy

论文评审过程：Received 9 October 2017, Revised 6 May 2018, Accepted 11 June 2018, Available online 18 June 2018, Version of Record 21 June 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.06.005