Multi-label regularized quadratic programming feature selection algorithm with Frank–Wolfe method
作者：
Highlights：
• A regularized multi-label quadratic programming feature selection model is presented.
• Efficient Frank–Wolfe method is applied to optimize this mode.
• A globally optimal feature selection operator is induced.
• Detailed experiments validate the effectiveness of our proposed method.
摘要
•A regularized multi-label quadratic programming feature selection model is presented.•Efficient Frank–Wolfe method is applied to optimize this mode.•A globally optimal feature selection operator is induced.•Detailed experiments validate the effectiveness of our proposed method.
论文关键词：Multi-label classification,Hybrid expert systems,Feature selection,Quadratic programming,Regularization,Frank–Wolfe method
论文评审过程：Received 8 July 2016, Revised 1 November 2017, Accepted 9 November 2017, Available online 10 November 2017, Version of Record 16 November 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.018
