Fifth IEEE International Conference on Data Mining (ICDM'05) (2005)
Nov. 27, 2005 to Nov. 30, 2005
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDM.2005.4
M. Halkidi , University of California at Riverside and Athens University of Economics and Business
D. Gunopulos , University of California at Riverside
N. Kumar , University of California at Riverside
M. Vazirgiannis , Athens University of Economics and Business
C. Domeniconi , George Mason University
In this paper, we propose a semi-supervised framework for learning a weighted Euclidean subspace, where the best clustering can be achieved. Our approach capitalizes on user-constraints and the quality of intermediate clustering results in terms of its structural properties. It uses the clustering algorithm and the validity measure as parameters.
D. Gunopulos, M. Vazirgiannis, M. Halkidi, N. Kumar and C. Domeniconi, "A Framework for Semi-Supervised Learning Based on Subjective and Objective Clustering Criteria," Fifth IEEE International Conference on Data Mining (ICDM'05)(ICDM), Houston, Texas, 2005, pp. 637-640.