Penalized partial least square discriminant analysis with ℓ1-norm for multi-label data
作者：
Highlights：
• A new and effective learning method for the multi-label data is proposed.
• The method exploits the sparse property of the label space fully.
• The method captures the correlations of the variables by using partial least squares discriminant analysis.
• Dimension reduction has also applied to the high-dimensional data.
• The sparse purpose is achieved by performing the l1-norm penalty.
摘要
Highlights•A new and effective learning method for the multi-label data is proposed.•The method exploits the sparse property of the label space fully.•The method captures the correlations of the variables by using partial least squares discriminant analysis.•Dimension reduction has also applied to the high-dimensional data.•The sparse purpose is achieved by performing the l1-norm penalty.
论文关键词：Partial least squares,Discriminant analysis,Dimension reduction,Sparse learning,Multi-label learning
论文评审过程：Received 11 February 2014, Revised 25 October 2014, Accepted 10 November 2014, Available online 18 November 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.11.007
