From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering

@misc{citeulike:112870, abstract = {We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel inductive implications, we are able to successfully incorporate constraints for a wide range of data set types. Our method greatly improves on the previously studied constrained k-means algorithm, generally requiring less than half as many constraints to achieve a given accuracy on a...}, author = {Klein, D. and Kamvar, S. and Manning, C. }, citeulike-article-id = {112870}, keywords = {active, active\_learning, clustering, constrained\_clustering, contraints, learning}, posted-at = {2007-10-04 18:35:33}, priority = {0}, title = {From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering}, url = {http://citeseer.ist.psu.edu/klein02from.html}, year = {2002} }

TY - GEN ID - citeulike:112870 L3 - citeulike-article-id:112870 N2 - We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel inductive implications, we are able to successfully incorporate constraints for a wide range of data set types. Our method greatly improves on the previously studied constrained k-means algorithm, generally requiring less than half as many constraints to achieve a given accuracy on a... TI - From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering KW - active KW - active_learning KW - clustering KW - constrained_clustering KW - contraints KW - learning AU - Klein, D AU - Kamvar, S AU - Manning, C PY - 2002/// UR - http://citeseer.ist.psu.edu/klein02from.html ER -