Multiple indefinite kernel learning for feature selection

作者：

Highlights：

• We propose a novel multiple indefinite kernel feature selection (MIK-FS) method.

• We utilize a sampling method to select landmark points for large-scale problems.

• We extend MIK-FS to multi-class feature selection scenarios.

• Extensive experiments are conducted to validate our methods.

摘要

•We propose a novel multiple indefinite kernel feature selection (MIK-FS) method.•We utilize a sampling method to select landmark points for large-scale problems.•We extend MIK-FS to multi-class feature selection scenarios.•Extensive experiments are conducted to validate our methods.

论文关键词：Feature selection,Multiple indefinite kernel learning,Indefinite kernel,DC programming

论文评审过程：Received 17 July 2019, Revised 22 November 2019, Accepted 24 November 2019, Available online 2 December 2019, Version of Record 8 February 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.105272