Clustering of high dimensional data is often performed by applying Singular Value Decomposition (SVD) on the original data space and building clusters from the derived eigenvectors. Often no single eigenvector separates the clusters. We propose a method that combines the self-similarity matrices of the eigenvector in such a way that the concepts are well separated. We compare it with a K-Means approach on public domain data sets and discuss when and why our method outperforms the K-Means on SVD method.
%0 Conference Paper
%1 Gabriel:2010:ECU:1774088.1774313
%A Gabriel, Hans-Henning
%A Spiliopoulou, Myra
%A Nanopoulos, Alexandros
%B Proceedings of the 2010 ACM Symposium on Applied Computing
%C New York, NY, USA
%D 2010
%I ACM
%K kmd
%P 1083--1087
%R 10.1145/1774088.1774313
%T Eigenvector-based Clustering Using Aggregated Similarity Matrices
%U http://doi.acm.org/10.1145/1774088.1774313
%X Clustering of high dimensional data is often performed by applying Singular Value Decomposition (SVD) on the original data space and building clusters from the derived eigenvectors. Often no single eigenvector separates the clusters. We propose a method that combines the self-similarity matrices of the eigenvector in such a way that the concepts are well separated. We compare it with a K-Means approach on public domain data sets and discuss when and why our method outperforms the K-Means on SVD method.
%@ 978-1-60558-639-7
@inproceedings{Gabriel:2010:ECU:1774088.1774313,
abstract = {Clustering of high dimensional data is often performed by applying Singular Value Decomposition (SVD) on the original data space and building clusters from the derived eigenvectors. Often no single eigenvector separates the clusters. We propose a method that combines the self-similarity matrices of the eigenvector in such a way that the concepts are well separated. We compare it with a K-Means approach on public domain data sets and discuss when and why our method outperforms the K-Means on SVD method.},
acmid = {1774313},
added-at = {2014-06-20T12:41:07.000+0200},
address = {New York, NY, USA},
author = {Gabriel, Hans-Henning and Spiliopoulou, Myra and Nanopoulos, Alexandros},
biburl = {https://www.bibsonomy.org/bibtex/269f62dc85c3068a729a0f72f5c6412ad/kmd-ovgu},
booktitle = {Proceedings of the 2010 ACM Symposium on Applied Computing},
doi = {10.1145/1774088.1774313},
interhash = {9c821ba66bbde1b94b84e17b26b9b384},
intrahash = {69f62dc85c3068a729a0f72f5c6412ad},
isbn = {978-1-60558-639-7},
keywords = {kmd},
location = {Sierre, Switzerland},
numpages = {5},
pages = {1083--1087},
publisher = {ACM},
series = {SAC '10},
timestamp = {2014-06-20T12:41:07.000+0200},
title = {Eigenvector-based Clustering Using Aggregated Similarity Matrices},
url = {http://doi.acm.org/10.1145/1774088.1774313},
year = 2010
}