%0 Conference Paper %1 584890 %A Hamerly, Greg %A Elkan, Charles %B CIKM '02: Proceedings of the eleventh international conference on Information and knowledge management %C New York, NY, USA %D 2002 %I ACM %K algorithm kmeans machinelearning %P 600--607 %R 10.1145/584792.584890 %T Alternatives to the k-means algorithm that find better clusterings %U http://portal.acm.org/citation.cfm?id=584890 %X We investigate here the behavior of the standard k-means clustering algorithm and several alternatives to it: the k-harmonic means algorithm due to Zhang and colleagues, fuzzy k-means, Gaussian expectation-maximization, and two new variants of k-harmonic means. Our aim is to find which aspects of these algorithms contribute to finding good clusterings, as opposed to converging to a low-quality local optimum. We describe each algorithm in a unified framework that introduces separate cluster membership and data weight functions. We then show that the algorithms do behave very differently from each other on simple low-dimensional synthetic datasets and image segmentation tasks, and that the k-harmonic means method is superior. Having a soft membership function is essential for finding high-quality clusterings, but having a non-constant data weight function is useful also. %@ 1-58113-492-4

@inproceedings{584890, abstract = {We investigate here the behavior of the standard k-means clustering algorithm and several alternatives to it: the k-harmonic means algorithm due to Zhang and colleagues, fuzzy k-means, Gaussian expectation-maximization, and two new variants of k-harmonic means. Our aim is to find which aspects of these algorithms contribute to finding good clusterings, as opposed to converging to a low-quality local optimum. We describe each algorithm in a unified framework that introduces separate cluster membership and data weight functions. We then show that the algorithms do behave very differently from each other on simple low-dimensional synthetic datasets and image segmentation tasks, and that the k-harmonic means method is superior. Having a soft membership function is essential for finding high-quality clusterings, but having a non-constant data weight function is useful also.}, added-at = {2010-10-13T07:59:03.000+0200}, address = {New York, NY, USA}, author = {Hamerly, Greg and Elkan, Charles}, biburl = {https://www.bibsonomy.org/bibtex/2f0d375b3eef2c34db4190bb9a2a0f527/cdevries}, booktitle = {CIKM '02: Proceedings of the eleventh international conference on Information and knowledge management}, description = {Alternatives to the k-means algorithm that find better clusterings}, doi = {10.1145/584792.584890}, interhash = {41a8806f8b6d98a660a0f46e4559998d}, intrahash = {f0d375b3eef2c34db4190bb9a2a0f527}, isbn = {1-58113-492-4}, keywords = {algorithm kmeans machinelearning}, location = {McLean, Virginia, USA}, pages = {600--607}, publisher = {ACM}, timestamp = {2010-10-13T07:59:03.000+0200}, title = {Alternatives to the k-means algorithm that find better clusterings}, url = {http://portal.acm.org/citation.cfm?id=584890}, year = 2002 }