Abstract
This paper presents a method for creating abstract concepts for classification rule mining. We try to find abstract concepts that are useful for the classification in the sense that assuming such a concept can well discriminate a target class and supports data as much as possible. Our task of finding useful concepts is formalized as an optimization problem in which its constraint and objective function are given by entropy and probability of class distributions, respectively. Concepts to be found can be stated in terms of maximal weighted cliques in a graph constructed from the possible distributions. From the graph, as useful abstract concepts, top-N maximal weighted cliques are efficiently extracted with two pruning techniques: branch-and-bound and entropy-based pruning. It is shown that our entropy-based pruning can safely prune only useless cliques by adding distributions in increasing order of their entropy in the process of clique expansion. Preliminary experimental results show that useful concepts can be created in our framework.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Han, J., Fu, Y.: Attribute-Oriented Induction. In: Data Mining, Advances in Knowledge Discovery and Data Mining, pp. 399–421. MIT Press, Cambridge (1996)
Quinlan, J.R.: C4.5 – Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Haraguchi, M.: Concept Learning Based on Optimal Clique Searches. SIG-FAIA202- 11, 63–66 (2002)
Haraguchi, M., Kudoh, Y.: Some Criterions for Selecting the Best Data Abstractions. In: Arikawa, S., Shinohara, A. (eds.) Progress in Discovery Science. LNCS (LNAI), vol. 2281, pp. 156–167. Springer, Heidelberg (2002)
Kudoh, Y., Haraguchi, M., Okubo, Y.: Data Abstractions for Decision Tree Induction. Theoretical Computer Science 292, 387–416 (2003)
Hettich, S., Bay, S.D.: The UCI KDD Archive Dept. of Information and Computer Science, Univ. of California (1999), http://kdd.ics.uci.edu
Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs (1988)
Wakai, Y., Tomita, E., Wakatsuki, M.: An Efficient Algorithm for Finding a Maximum Weight Clique. In: Proc. of the 12th Annual Conf. of JSAI, pp. 250–252 (1998) (in Japanese)
Takabatake, K.: Clustering of Distributions in Summarizing Information. In: Proc. of IBIS 2001, pp. 309–314 (2001) (in Japanese)
Morimoto, Y.: Algorithm for mining association rules for binary segmentations of huge categorical databases. In: Proc. of VLDB 1998, pp.380–391 (1998)
Michalski, R.S., Kaufman, K.A.: Data Mining and Knowledge Discovery: A Review of Issues and a Multistrategy Approach. In: Machine Learning and Data Mining: Methods and Applications, pp. 71–112. Wiley, Chichester (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Okubo, Y., Haraguchi, M. (2003). Creating Abstract Concepts for Classification by Finding Top-N Maximal Weighted Cliques. In: Grieser, G., Tanaka, Y., Yamamoto, A. (eds) Discovery Science. DS 2003. Lecture Notes in Computer Science(), vol 2843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39644-4_41
Download citation
DOI: https://doi.org/10.1007/978-3-540-39644-4_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20293-6
Online ISBN: 978-3-540-39644-4
eBook Packages: Springer Book Archive