An Experimental Comparison of Model-Based Clustering Methods Export

@article{citeulike:3906689, abstract = {We compare the three basic algorithms for model-based clustering on high-dimensional discrete-variable datasets. All three algorithms use the same underlying model: a naive-Bayes model with a hidden root node, also known as a multinomial-mixture model. In the first part of the paper, we perform an experimental comparison between three batch algorithms that learn the parameters of this model: the Expectation–Maximization (EM) algorithm, a ” winner take all” version of the EM algorithm reminiscent of the K-means algorithm, and model-based agglomerative clustering. We find that the EM algorithm significantly outperforms the other methods, and proceed to investigate the effect of various initialization methods on the final solution produced by the EM algorithm. The initializations that we consider are (1) parameters sampled from an uninformative prior, (2) random perturbations of the marginal distribution of the data, and (3) the output of agglomerative clustering. Although the methods are substantially different, they lead to learned models that are similar in quality.}, author = {Meil\u{a}, Marina and Heckerman, David}, citeulike-article-id = {3906689}, citeulike-linkout-0 = {http://dx.doi.org/10.1023/A:1007648401407}, citeulike-linkout-1 = {http://www.springerlink.com/content/h7500163314n0l20}, day = {1}, doi = {10.1023/A:1007648401407}, journal = {Machine Learning}, keywords = {clustering, comparison, evaluation, segmentation, validation}, month = {January}, number = {1}, pages = {9--29}, posted-at = {2009-01-19 02:10:04}, priority = {2}, title = {An Experimental Comparison of Model-Based Clustering Methods}, url = {http://dx.doi.org/10.1023/A:1007648401407}, volume = {42}, year = {2001} }

TY - JOUR ID - citeulike:3906689 L3 - citeulike-article-id:3906689 N2 - We compare the three basic algorithms for model-based clustering on high-dimensional discrete-variable datasets. All three algorithms use the same underlying model: a naive-Bayes model with a hidden root node, also known as a multinomial-mixture model. In the first part of the paper, we perform an experimental comparison between three batch algorithms that learn the parameters of this model: the Expectation–Maximization (EM) algorithm, a “winner take all” version of the EM algorithm reminiscent of the K-means algorithm, and model-based agglomerative clustering. We find that the EM algorithm significantly outperforms the other methods, and proceed to investigate the effect of various initialization methods on the final solution produced by the EM algorithm. The initializations that we consider are (1) parameters sampled from an uninformative prior, (2) random perturbations of the marginal distribution of the data, and (3) the output of agglomerative clustering. Although the methods are substantially different, they lead to learned models that are similar in quality. IS - 1 JF - Machine Learning EP - 29 TI - An Experimental Comparison of Model-Based Clustering Methods VL - 42 SP - 9 KW - clustering KW - comparison KW - evaluation KW - segmentation KW - validation AU - Meilă, Marina AU - Heckerman, David PY - 2001/01/01/ UR - http://dx.doi.org/10.1023/A:1007648401407 ER -