Multiview Clustering: A Late Fusion Approach Using Latent Models

被引：69

作者：

Bruno, Eric ^{[1
]}

Marchand-Maillet, Stephane ^{[1
]}

机构：

[1] Univ Geneva, Comp Sci Dpt, Viper Grp, Geneva, Switzerland

来源：

PROCEEDINGS 32ND ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL | 2009年

关键词：

Multi-view clustering; data fusion; latent models;

D O I：

10.1145/1571941.1572103

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Multi-view clustering is an important problem in information retrieval due to the abundance of data offering many perspectives and generating multi-view representations. We investigate in this short note a late fusion approach for multi-view clustering based on the latent modeling of cluster-cluster relationships. We derive a probabilistic multi-view clustering model outperforming an early-fusion approach based on multi-view feature correlation analysis.

引用

页码：736 / 737

页数：2

共 8 条

[1]

Bekkerman R., 2005, ICML, P41

[2] Multi-view clustering [J].

Bickel, S ;

Scheffer, T .

FOURTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2004, :19-26

[3]

Gaussier E., 2005, SIGIR 2005. Proceedings of the Twenty-Eighth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, P601, DOI 10.1145/1076034.1076148

[4] Unsupervised learning by probabilistic latent semantic analysis [J].

Hofmann, T .

MACHINE LEARNING, 2001, 42 (1-2) :177-196

[5]

Homburg Helge., 2005, ISMIR, P528

[6]

Lange T., 2006, ADV NEURAL INFORM PR, V18, P723

[7]

Lee DD, 2001, ADV NEUR IN, V13, P556

[8]

ZHOU D, 2007, ICML 07, P1159, DOI DOI 10.1145/1273496.1273642

← 1 →