Advertisement

Bayesian Network Learning with Abstraction Hierarchies and Context-Specific Independence

  • Marie desJardins
  • Priyang Rathod
  • Lise Getoor
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3720)

Abstract

Context-specific independence representations, such as tree-structured conditional probability tables (TCPTs), reduce the number of parameters in Bayesian networks by capturing local independence relationships and improve the quality of learned Bayesian networks. We previously presented Abstraction-Based Search (ABS), a technique for using attribute value hierarchies during Bayesian network learning to remove unimportant distinctions within the CPTs. In this paper, we introduce TCPT ABS (TABS), which integrates ABS with TCPT learning. Since expert-provided hierarchies may not be available, we provide a clustering technique for deriving hierarchies from data. We present empirical results for three real-world domains, finding that (1) combining TCPTs and ABS provides a significant increase in the quality of learned Bayesian networks (2) combining TCPTs and ABS provides a dramatic reduction in the number of parameters in the learned networks, and (3) data-derived hierarchies perform as well or better than expert-provided hierarchies.

Keywords

Bayesian Network Leaf Node Abstraction Level Minimum Description Length Agglomerative 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.

References

  1. 1.
    Bouckaert, R.R.: Probabilistic network construction using the minimum description length principle. Technical Report RUU-CS-94-27, Utrecht University (1994)Google Scholar
  2. 2.
    Boutilier, C., Friedman, N., Goldszmidt, M., Koller, D.: Context-specific independence in Bayesian networks. In: Proceedings of UAI 1996, pp. 115–123 (1996)Google Scholar
  3. 3.
    Chickering, D.M., Geiger, D., Heckerman, D.: Learning Bayesian Networks is NP-Hard. Technical Report MSR-TR-94-17, Microsoft Research (November 1994)Google Scholar
  4. 4.
    Chickering, D.M., Heckerman, D., Meek, C.: A Bayesian approach to learning Bayesian networks with local structure. In: Proceedings of UAI 1997, pp. 80–89 (1997)Google Scholar
  5. 5.
    Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Machine Learning 9(4), 309–347 (1992)zbMATHGoogle Scholar
  6. 6.
    desJardins, M., Getoor, L., Koller, D.: Using feature hierarchies in Bayesian network learning. In: Choueiry, B.Y., Walsh, T. (eds.) SARA 2000. LNCS (LNAI), vol. 1864, pp. 260–270. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  7. 7.
    Friedman, N., Goldszmidt, M.: Learning bayesian networks with local structure. In: Proceedings of UAI 1996, pp. 252–262 (1996)Google Scholar
  8. 8.
    Heckerman, D.: A Tutorial on Learning Bayesian Networks. Technical Report MSR-TR-95-06, Microsoft Research (March 1995)Google Scholar
  9. 9.
    Hettich, S., Blake, C.L., Merz, C.J.: UCI repository of machine learning databases (1998)Google Scholar
  10. 10.
    Kang, D.K., Silvescu, A., Zhang, J., Honavar, V.: Generation of attribute value taxonomies from data for data-driven construction of accurate and compact classifiers. In: Proceedings of ICDM 2004 (2004)Google Scholar
  11. 11.
    Lam, W., Bacchus, F.: Learning Bayesian belief networks: An approach based on the MDL principle. In: Computational Intelligence, pp. 269–293 (1994)Google Scholar
  12. 12.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
  13. 13.
    Zhang, J., Honavar, V.: Learning decision tree classifiers from attribute value taxonomies and partially specified data. In: Proceedings of ICML 2003 (2003)Google Scholar
  14. 14.
    Zhang, J., Honavar, V.: AVT-NBL: An algorithm for learning compact and accurate naive Bayes classifiers from attribute value taxonomies and data. In: Proceedings of ICDM 2004 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Marie desJardins
    • 1
  • Priyang Rathod
    • 1
  • Lise Getoor
    • 2
  1. 1.Department of Computer Science and Electrical EngineeringUniversity of MarylandBaltimore County
  2. 2.Computer Science DepartmentUniversity of MarylandCollege Park

Personalised recommendations