Learning with privileged information for multi-Label classification
作者：
Highlights：
• We tackle the problem of multi-label classification with the help of privileged information.
• Similarity constraints capture the relationship between available and privileged information.
• Ranking orders between present and absent labels exploit the dependencies among multiple labels.
摘要
•We tackle the problem of multi-label classification with the help of privileged information.•Similarity constraints capture the relationship between available and privileged information.•Ranking orders between present and absent labels exploit the dependencies among multiple labels.
论文关键词：Privileged information,Multi-label classification,Similarity constraints
论文评审过程：Received 20 July 2017, Revised 13 February 2018, Accepted 27 March 2018, Available online 28 March 2018, Version of Record 6 April 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.03.033
