C3E: A Framework for Combining Ensembles of Classifiers and Clusterers
The combination of multiple classifiers to generate a single classifier has been shown to be very useful in practice. Similarly, several efforts have shown that cluster ensembles can improve the quality of results as compared to a single clustering solution. These observations suggest that ensembles containing both classifiers and clusterers are potentially useful as well. Specifically, clusterers provide supplementary constraints that can improve the generalization capability of the resulting classifier. This paper introduces a new algorithm named C 3 E that combines ensembles of classifiers and clusterers. Our experimental evaluation of C 3 E shows that it provides good classification accuracies in eleven tasks derived from three real-world applications. In addition, C 3 E produces better results than the recently introduced Bipartite Graph-based Consensus Maximization (BGCM) Algorithm, which combines multiple supervised and unsupervised models and is the algorithm most closely related to C 3 E.
KeywordsEnsembles Classification Clustering
Unable to display preview. Download preview PDF.
- 1.Banerjee, A., Merugu, S., Dhillon, I., Ghosh, J.: Clustering with Bregman divergences. In: JMLR (2005)Google Scholar
- 2.Schlkopf, B., Zien, A., Chapelle, O.: Semi-Supervised Learning. MIT Press. Cambridge (2006)Google Scholar
- 4.Fern, X.Z., Brodley, C.E.: Solving cluster ensemble problems by bipartite graph partitioning. In: Proc. of the ICML, pp. 36–43 (2004)Google Scholar
- 5.Gao, J., Liang, F., Fan, W., Sun, Y., Han, J.: Graph-based consensus maximization among multiple supervised and unsupervised models. In: Proc. of NIPS, pp. 1–9 (2009)Google Scholar
- 11.Davidson, I., Basu, S., Wagstaff, K.L. (eds.): Clustering with Balancing Constraints. CRC Press, Boca Raton (2008)Google Scholar
- 12.Strehl, A., Ghosh, J.: Cluster ensembles – a knowledge reuse framework for combining multiple partitions. In: JMLR, vol. 617, pp. 583–617 (2002)Google Scholar