Weighted feature selection via discriminative sparse multi-view learning
作者：
Highlights：
• A novel supervised sparse multi-view feature selection method is proposed.
• The method adopts the view weighted separable strategy.
• The method integrates both the complementarity and specificity of views.
• The method solves small-scale problems instead of a large one to reduce complexity.
• The validity is shown by the comparison with several state-of-the-art methods.
摘要
•A novel supervised sparse multi-view feature selection method is proposed.•The method adopts the view weighted separable strategy.•The method integrates both the complementarity and specificity of views.•The method solves small-scale problems instead of a large one to reduce complexity.•The validity is shown by the comparison with several state-of-the-art methods.
论文关键词：Supervised structured sparsity-inducing feature selection,Multi-view,Weighted loss,Separable penalty strategy
论文评审过程：Received 23 January 2019, Revised 23 April 2019, Accepted 26 April 2019, Available online 30 April 2019, Version of Record 4 June 2019.
论文官网地址：https://doi.org/10.1016/j.knosys.2019.04.024
