Multi-view fuzzy clustering with minimax optimization for effective clustering of data from multiple sources

作者:

Highlights:

• New fuzzy clustering based on minimax optimization for data given by multiple views.

• The maximum disagreements of different weighted views are minimized.

• The weight of each view is learned automatically.

• Only one additional parameter needs to be set besides the fuzzier.

• Experimental studies show MinimaxFCM performs better than related approaches.

摘要

•New fuzzy clustering based on minimax optimization for data given by multiple views.•The maximum disagreements of different weighted views are minimized.•The weight of each view is learned automatically.•Only one additional parameter needs to be set besides the fuzzier.•Experimental studies show MinimaxFCM performs better than related approaches.

论文关键词:Multi-view clustering,Fuzzy clustering,Soft clustering,Minimax optimization

论文评审过程:Received 11 July 2016, Revised 14 September 2016, Accepted 4 October 2016, Available online 27 October 2016, Version of Record 2 January 2017.

论文官网地址:https://doi.org/10.1016/j.eswa.2016.10.006