多视图聚类算法综述-软件导刊.PDFVIP

  • 230
  • 0
  • 约1.95万字
  • 约 4页
  • 2019-08-18 发布于北京
  • 举报
多视图聚类算法综述-软件导刊.PDF

第18卷第4 期 软 件 导 刊 Vol. 18 No. 4 第 4 期 2019 年4 月 Software Guide Apr. 2019 多视图聚类算法综述 何雪梅 (西华师范大学计算机学院,四川 南充637002 ) 摘 要:在大数据时代,数据是由不同来源生成的,或者是从不同视图中观察得到的,这些数据被称为多视图数 据。在数据挖掘与分析中,充分发挥知识在多视图数据中的作用是非常重要的,因此需要在融合相关数据的同 时,考虑不同视图的多样性。近年来,多视图聚类(MvC )受到越来越多学者关注,根据其涉及的机制和原则,将 多视图聚类算法分为5 类,即协同训练算法、多核学习、多视图聚类、多视图子空间聚类与多任务多视图聚类。 对多视图聚类算法进行介绍,并重点介绍了协同训练算法与多核学习。 关键词:数据挖掘;聚类分析;多视图聚类;协同训练;多核学习 DOI:10. 11907/rjdk. 182831 中图分类号:TP312 文献标识码:A 文章编号:1672-7800 (2019 )004-0079-03 ASurveyofMulti-viewClusteringAlgorithms HE Xue-mei (School of Computer Science ,China West Normal University ,Nanchong 637002 ,China ) Abstract:In the era of big data ,data is generated from different sources or observed from different views ,and they are called multi-view data. In data mining and analysis ,it is very important to make full use of the role of knowledge in multi-view data. This re⁃ quires advanced techniques that take into account the diversity of different views while merging these data. In recent years ,multi-view clustering (MvC )has attracted more and more attention. According to the mechanisms and principles involved ,multi-view clustering algorithms are divided into five categories ,namely ,cooperative training algorithm ,multi-core learning ,view graph clustering , multi-view subspace clustering and multi-task multi-view clustering. In this article ,we will focus on collaborative training algorithms and multi-core learning. KeyWords:data mining ;cluster analysis ;multi-view clustering ;co-training ;multi-kernel learning

文档评论(0)

1亿VIP精品文档

相关文档