A novel robust kernel for classifying high-dimensional data using Support Vector Machines

作者：

Highlights：

• A new semantic similarity based co-clustering kernel is proposed.

• A mathematical proof for mercer's kernel is provided.

• The algorithm embeds the task of identifying bias in the learning phase.

• Experiments show the effectiveness of the algorithm on several real datasets.

摘要

•A new semantic similarity based co-clustering kernel is proposed.•A mathematical proof for mercer's kernel is provided.•The algorithm embeds the task of identifying bias in the learning phase.•Experiments show the effectiveness of the algorithm on several real datasets.

论文关键词：Semantic kernels,Support Vector Machines,Co-clustering,Label noise

论文评审过程：Received 20 June 2018, Revised 6 March 2019, Accepted 16 April 2019, Available online 18 April 2019, Version of Record 30 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.04.037