Active Semi-Supervision for Pairwise Constrained Clustering
S. Basu, A. Banerjee, and R. Mooney. Proceedings of the 2004 SIAM International Conference on Data Mining, page 333--344. Lake Buena Vista, FL, Society for Industrial and Applied Mathematics, (April 2004)
DOI: 10.1137/1.9781611972740.31
Abstract
Semi-supervised clustering uses a small amount of supervised data to aid unsupervised learning. One typical approach specifies a limited number of must-link and cannot-link constraints between pairs of examples. This paper presents a pairwise constrained clustering framework and a new method for actively selecting informative pairwise constraints to get improved clustering performance. The clustering and active learning methods are both easily scalable to large datasets, and can handle very high dimensional data. Experimental and theoretical results confirm that this active querying of pairwise constraints significantly improves the accuracy of clustering when given a relatively small amount of supervision.
%0 Conference Paper
%1 Basu:EtAl:04
%A Basu, Sugato
%A Banerjee, Arindam
%A Mooney, Raymond J.
%B Proceedings of the 2004 SIAM International Conference on Data Mining
%C Lake Buena Vista, FL
%D 2004
%I Society for Industrial and Applied Mathematics
%K clustering kmeans pckmeans semi-supervised shabnam unsupervised
%P 333--344
%R 10.1137/1.9781611972740.31
%T Active Semi-Supervision for Pairwise Constrained Clustering
%U http://www.cs.utexas.edu/users/ml/papers/semi-sdm-04.pdf
%X Semi-supervised clustering uses a small amount of supervised data to aid unsupervised learning. One typical approach specifies a limited number of must-link and cannot-link constraints between pairs of examples. This paper presents a pairwise constrained clustering framework and a new method for actively selecting informative pairwise constraints to get improved clustering performance. The clustering and active learning methods are both easily scalable to large datasets, and can handle very high dimensional data. Experimental and theoretical results confirm that this active querying of pairwise constraints significantly improves the accuracy of clustering when given a relatively small amount of supervision.
@inproceedings{Basu:EtAl:04,
abstract = {Semi-supervised clustering uses a small amount of supervised data to aid unsupervised learning. One typical approach specifies a limited number of must-link and cannot-link constraints between pairs of examples. This paper presents a pairwise constrained clustering framework and a new method for actively selecting informative pairwise constraints to get improved clustering performance. The clustering and active learning methods are both easily scalable to large datasets, and can handle very high dimensional data. Experimental and theoretical results confirm that this active querying of pairwise constraints significantly improves the accuracy of clustering when given a relatively small amount of supervision.},
added-at = {2019-08-22T14:45:12.000+0200},
address = {Lake Buena Vista, FL},
author = {Basu, Sugato and Banerjee, Arindam and Mooney, Raymond J.},
biburl = {https://www.bibsonomy.org/bibtex/2ac322f4bc04d4affb7fb43c35bca87e0/ghagerer},
booktitle = {Proceedings of the 2004 {SIAM} International Conference on Data Mining},
description = {1.9781611972740.31},
doi = {10.1137/1.9781611972740.31},
interhash = {57ac0df74fe51c03c9044ca1f789c585},
intrahash = {ac322f4bc04d4affb7fb43c35bca87e0},
keywords = {clustering kmeans pckmeans semi-supervised shabnam unsupervised},
month = apr,
pages = {333--344},
publisher = {Society for Industrial and Applied Mathematics},
timestamp = {2019-09-05T11:23:22.000+0200},
title = {Active Semi-Supervision for Pairwise Constrained Clustering},
url = {http://www.cs.utexas.edu/users/ml/papers/semi-sdm-04.pdf},
year = 2004
}