Multi-view clustering via spectral partitioning and local refinement.pdfVIP

下载本文档

16
0
约3.44万字
约 10页
2017-03-16 发布于天津
举报
版权申诉

Multi-view clustering via spectral partitioning and local refinement.pdf

1、本文档共10页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Multi-view clustering via spectral partitioning and local refinement.pdf

Information Processing and Management 52 (2016) 618–627 Contents lists available at ScienceDirect Information Processing and Management journal homepage: /locate/ipm Multi-view clustering via spectral partitioning and local re?nement Nacim Fateh Chikhi? Department of Computer Science, Faculty of Sciences, University of Blida 1, BP 270 Route de Soumaa, 09000 Blida, Algeria article info Article history: Received 30 January 2015 Revised 24 November 2015 Accepted 1 December 2015 Available online 15 January 2016 Keywords: Multi-view clustering Spectral clustering Local re?nement Normalized cuts abstract Cluster analysis using multiple representations of data is known as multi-view clustering and has attracted much attention in recent years. The major drawback of existing multiview algorithms is that their clustering performance depends heavily on hyperparameters which are di?cult to set. In this paper, we propose the Multi-View Normalized Cuts (MVNC) approach, a twostep algorithm for multi-view clustering. In the ?rst step, an initial partitioning is performed using a spectral technique. In the second step, a local search procedure is used to re?ne the initial clustering. MVNC has been evaluated and compared to state-of-the-art multi-view clustering approaches using three real-world datasets. Experimental results have shown that MVNC signi?cantly outperforms existing algorithms in terms of clustering quality and computational e?ciency. In addition to its superior performance, MVNC is parameter-free which makes it easy to use. ? 2015 Elsevier Ltd. All rights reserved. 1. Introduction In many real-world applications, datasets are characterized by multiple sets of features. Web pages and scienti?c papers are typical examples of such datasets where documents can be represented using not only their textual content but also other modalities such link information. Cluster analysis using multiple representations (or views) of data is known as multi-view clustering and has attrac