@techreport{ilprints528,
          number = {2002-10},
           month = {February},
          author = {Dan Klein and Sepandar D. Kamvar and Christopher D. Manning},
           title = {From Instance-level Constraints to Space-Level Constraints: Making the Most of Prior Knowledge in Data Clustering},
            type = {Technical Report},
       publisher = {Stanford},
     institution = {Stanford InfoLab},
            year = {2002},
        keywords = {clustering, constrained clustering, prior knowledge},
             url = {http://ilpubs.stanford.edu:8090/528/},
        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 space-level 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 range of real-world data, while also being more robust when over-constrained.  We additionally discuss an active learning algorithm which increases the value of constraints even further.}
}