Abstract
This paper is concerned with the robustness of concept formation systems in the presence of concept drift. By concept drift is meant that the intension of a concept is not stable during the period of learning, a restriction which is otherwise often imposed. The work is based upon the architecture of Cobweb, an incremental, probabilistic conceptual clustering system. When incrementally and sequentially exposed to the extensions of a set of concepts, Cobweb retains all examples, disregards the age of a concept and may create different conceptual structures dependent on the order of examples. These three characteristics make Cobweb sensitive to the effects of concept drift. Six mechanisms that can detect concept drift and adjust the conceptual structure are proposed. A variant of one of these mechanisms: dynamic deletion of old examples, is implemented in a modified Cobweb system called Cobbit. The relative performance of Cobweb and Cobbit in the presence of concept drift is evaluated. In the experiment the error index, i.e. the average of the ability to predict each attribute is used as the major instrument. The experiment is performed in a synthetical domain and indicates that Cobbit regain performance faster after a discrete concept shift.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
John A. Allen and Kevin Thompson. Probabilistic concept formation in relational domains. In Machine Learning—Proceedings of the Eighth International Workshop (ML91), pages 375–379. Morgan Kaufmann Publishers, Inc, 1991.
Gautam Biswas, Jerry Weinberg, Qun Yang, and Glenn R. Koller. Conceptual clustering and exploratory data analysis. In Machine Learning—Proceedings of the Eighth International Workshop (ML91), pages 591–595. Morgan Kaufmann Publishers, Inc, 1991.
Scott Clearwater, Tze-Pin Cheng, Haym Hirsch, and Bruce Buchanan. Incremental batch learning. In Proceedings of the Sixth International Workshop on Machine Learning, pages 366–370. Morgan Kaufmann Publishers, Inc, 1989.
Douglas Fisher. Noise-tolerant conceptual clustering. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, volume 1, pages 825–830. Morgan Kaufmann Publishers, Inc, 1989.
Douglas Fisher, Ling Xu, and Nazih Zard. Ordering effects in clustering. In Machine Learning: Proceedings of the Ninth International Workshop (ML92), pages 163–168. Morgan Kaufmann Publishers, Inc, 1992.
Douglas Hayes Fisher. Knowledge Acquisition via Incremental Conceptual Clustering. PhD thesis, University of California, Irvine, 1987.
John Gennari, Pat Langley, and Doug Fisher. Models of incremental concept formation. Artificial Intelligence, (40):11–61, 1989.
Mirsad Hadzikadic and David Y. Y. Yun. Concept formation by incremental conceptual clustering. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pages 831–836, 1989.
Stephen José Hanson and Malcolm Bauer. Machine learning, clustering and polymorphy. In Uncertainty in artificial intelligence, pages 415–428. Elsevier Science Publishers, 1986.
Stephen José Hanson and Malcolm Bauer. Conceptual clustering, categorization and polymorphy. Machine Learning, (3):343–372, 1989.
Dennis Kibler and Pat Langley. Machine learning as an experimental science. In Proceedings of the Third European Working Session on Learning. Morgan Kaufmann Publishers, Inc, 1988.
Miroslav Kubat and Ivana Krizakova. Forgetting and ageing of knowledge in concept formation. Technical report, Computer Centre, Brno Technical University, Udolni 19, 60200 Brno, 1989.
Miroslav Kubat and Jirina Pavlickova. System flora: Learning from time-varying training sets. In Yves Kodratoff, editor, Machine Learning—EWSL-91, number 482 in Lecture Notes in Artificial Intelligence. Springer-Verlag, 1991.
Michael Lebowitz. Concept learning in a rich input domain: Generalization-based memory. Technical report, Department of Computer Science, Columbia University, New York, 1984.
Michael Lebowitz. Experiments with incremental concept formation: Unimem. Machine Learning, (2):103–138, 1987.
Ryszard S. Michalski and Robert E. Stepp. Learning from observation: Conceptual clustering. In Jaime G. Carbonell, Ryszard S. Michalski, and Tom M. Mitchell, editors, Machine Learning: An Artificial Intelligence Approach, pages 331–363. Tioga publishing company, 1983.
Ryszard S. Michalski and Robert E. Stepp. A theory and methodology of inductive learning. In Jaime G. Carbonell, Ryszard S. Michalski, and Tom M. Mitchell, editors, Machine Learning: An Artificial Intelligence Approach, pages 83–129. Tioga publishing company, 1983.
Bernd Nordhausen. Conceptual clustering using relational information. In Proceedings aaai-86 Fifth National Conference on Artificial intelligence, pages 508–512, 1986.
Jeffrey Schlimmer and Richard Granger, Junior. Beyond incremental processing: Tracking concept drift. In Proceedings aaai-86 Fifth National Conference on Artificial intelligence, pages 502–507, 1986.
Jeffrey Schlimmer and Richard Granger, Junior. Incremental learning from noisy data. Machine Learning, 1(3):317–354, 1986.
Gerhard Widmer and Miroslav Kubat. Effective learning in dynamic environments by explicit context tracking. In Proceedings of the European Conference on Machine Learning (ECML-93, Vienna, Austria, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kilander, F., Jansson, C.G. (1993). COBBIT—A control procedure for COBWEB in the presence of concept drift. In: Brazdil, P.B. (eds) Machine Learning: ECML-93. ECML 1993. Lecture Notes in Computer Science, vol 667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56602-3_140
Download citation
DOI: https://doi.org/10.1007/3-540-56602-3_140
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56602-1
Online ISBN: 978-3-540-47597-2
eBook Packages: Springer Book Archive