%0 Journal Article %1 citeulike:251432 %A Basu, Sugato %A Banerjee, Arindam %A Mooney, Raymond J. %B Proceedings of the SIAM International Conference on Data Mining %C Lake Buena Vista, FL %D 2004 %K contraint semisupervised similarity %P 333--344 %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 cannotlink 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.

@article{citeulike:251432, 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 cannotlink 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 = {2006-06-16T10:34:37.000+0200}, address = {Lake Buena Vista, FL}, author = {Basu, Sugato and Banerjee, Arindam and Mooney, Raymond J.}, biburl = {https://www.bibsonomy.org/bibtex/2c3a38d2081aba3ce847f23eb50512b0b/ldietz}, booktitle = {Proceedings of the SIAM International Conference on Data Mining}, citeulike-article-id = {251432}, comment = {assumption: same confidence for each user-constraint assumption: consistent data (add noise model in next version) They use the closure of the similarity contraints (problem with inconsistent data) use farthest first traversal (with a random start) for active queries}, interhash = {57ac0df74fe51c03c9044ca1f789c585}, intrahash = {c3a38d2081aba3ce847f23eb50512b0b}, keywords = {contraint semisupervised similarity}, month = {April}, pages = {333--344}, priority = {3}, timestamp = {2006-06-16T10:34:37.000+0200}, title = {Active Semi-Supervision for Pairwise Constrained Clustering}, url = {http://www.cs.utexas.edu/users/ml/papers/semi-sdm-04.pdf}, year = 2004 }