A buffering strategy to avoid ordering effects in clustering

  • Luis Talaveral
  • Josep Roure
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1398)


It is widely reported in the literature that incremental clustering systems suffer from instance ordering effects and that under some orderings, extremely poor clusterings may be obtained. In this paper we present a new strategy aimed to mitigate these effects, the Not-Yet strategy which has a general and open formulation and it is not coupled to any particular system. Results suggest that the strategy improves the clustering quality and also that performance is limited by its limited foresight. We also show that, when combined with other strategies, the Not-Yet strategy may help the system to get high quality clusterings.


Cluster System Incremental Learning Cluster Quality Conceptual Cluster Incremental Cluster 
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.


  1. 1.
    J. R. Anderson and M. Matessa. Explorations of an incremental, bayesian algorithm for categorization. Machine Learning, (9):275–308, 1992.Google Scholar
  2. 2.
    J. Béjar. Adquisición automática de conocimiento en dominios poco estructurados. PhD thesis, Facultat d'Informàtica de Barcelona, UPC, 1995.Google Scholar
  3. 3.
    D. H. Fisher. Knowledge acquisition via incremental conceptual clustering. Machine Learning, (2):139–172, 1987.Google Scholar
  4. 4.
    D. H. Fisher. Optimization and simplification of hierarchical clusterings. Journal of Artificial Intelligence Research, (4):147–180, 1995.Google Scholar
  5. 5.
    D. H. Fisher and P. Langley. Conceptual clustering and its relation to numerical taxonomy. In W. A. Gale, editor, Artificial Intelligence and Statistics. Addison-Wesley, Reading,MA, 1986.Google Scholar
  6. 6.
    D. H. Fisher, L. Xu, and N. Zard. Ordering effects in clustering. In Proceedings of the Ninth International Conference on Machine Learning, pages 163–168, 1992.Google Scholar
  7. 7.
    J. H. Gennari, P. Langley, and D. Fisher. Models of incremental concept formation. Artificial Intelligence, (40):11–61, 1989.Google Scholar
  8. 8.
    P. Langley. Order effects in incremental learning. In P. Reimann and H. Spada, editors, Learning in humans and machines: Towards an Interdisciplinary Learning Science. Pergamon, 1995.Google Scholar
  9. 9.
    M. Lebowitz. Deferred commitment in unimem: waiting to learn. In Proceedings of the Fifth International Conference on Machine Learning, pages 80–86, 1988.Google Scholar
  10. 10.
    J. Roure. Study of methods and heuristics to improve the fuzzy classifications of LINNEO+. Master's thesis, Facultat d'Informática de Barcelona, UPC, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Luis Talaveral
    • 1
  • Josep Roure
    • 2
  1. 1.Departament de Llenguatges i Sistemes InformàticsUniversitat Politècnica de CatalunyaBarcelona, CataloniaSpain
  2. 2.Departament d'Informàtica de GestióEscola Universitària Politècnica de MataróMataró, CataloniaSpain

Personalised recommendations