DocumentCode :
2081220
Title :
Spectral Methods for Automatic Multiscale Data Clustering
Author :
Azran, Arik ; Ghahramani, Zoubin
Author_Institution :
University College London London WC1N 3AR, UK
Volume :
1
fYear :
2006
fDate :
17-22 June 2006
Firstpage :
190
Lastpage :
197
Abstract :
Spectral clustering is a simple yet powerful method for finding structure in data using spectral properties of an associated pairwise similarity matrix. This paper provides new insights into how the method works and uses these to derive new algorithms which given the data alone automatically learn different plausible data partitionings. The main theoretical contribution is a generalization of a key result in the field, the multicut lemma [7]. We use this generalization to derive two algorithms. The first uses the eigenvalues of a given affinity matrix to infer the number of clusters in data, and the second combines learning the affinity matrix with inferring the number of clusters. A hierarchical implementation of the algorithms is also derived. The algorithms are theoretically motivated and demonstrated on nontrivial data sets.
Keywords :
Clustering algorithms; Computer vision; Data engineering; Educational institutions; Eigenvalues and eigenfunctions; Machine learning; Machine learning algorithms; Partitioning algorithms; Power engineering and energy; Power engineering computing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on
ISSN :
1063-6919
Print_ISBN :
0-7695-2597-0
Type :
conf
DOI :
10.1109/CVPR.2006.289
Filename :
1640759
Link To Document :
بازگشت