TreeNets: A framework for anytime evaluation of belief networks

  • N. Jitnah
  • A. Nicholson
Accepted Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1244)


We present a new framework for evaluation of belief networks (BNs). It consists of two steps: (1) transforming a belief network into a tree structure called a treeNet (2) performing anytime inference by searching the treeNet. The root of the treeNet represents the query node. Whenever new evidence is incorporated, the posterior probability of the query node is re-calculated, using a variation of the polytree message-passing algorithm. The treeNet framework is geared towards anytime evaluation. Evaluating the treeNet is a tree search problem and we investigate different tree search strategies. Using a best-first method, we can to increase the rate of convergence of the anytime result.


uncertainty Bayesian Networks anytime algorithms practical reasoning graphical models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    I. Beinlich, H. Suermondt, R. Chavez, and G. Cooper. The alarm monitoring system: A case study with two probabilistic inference techniques for belief networks. In Proc. of the 2nd European Conf. on AI in medicine, pages 689–693, 1992.Google Scholar
  2. 2.
    A. Bhattacharyya. On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of the Calcutta Mathematics Society, 35:99–110, 1943.Google Scholar
  3. 3.
    B. Boerlage. Link strengths in bayesian networks. Master's thesis, Dept. of Computer Science, U. of British Columbia, 1995.Google Scholar
  4. 4.
    C. Boutilier, N. Friedman, M. Goldszmidt, and D. Koller. Context-specific independence in bayesian networks. In Proc. of 12th Conf. on UAI, pages 115–123, 1996.Google Scholar
  5. 5.
    Homer L. Chin and Gregory F. Cooper. Bayesian belief network inference using simulation. In Uncertainty in Artificial Intelligence 3, pages 129–147, 1989.Google Scholar
  6. 6.
    G.F. Cooper. The computational complexity of probabilistic inference using bayesian belief networks. Artificial Intelligence, 42:393–405, 1990.Google Scholar
  7. 7.
    P. Dagum and M. Luby. Approximating probabilistic inference in belief networks is NP-hard. Artificial Intelligence, pages 141–153, 1993.Google Scholar
  8. 8.
    A. Darwiche and G. Provan. Query-dags: A practical paradigm for implementing belief-network inference. In Proc. of 12th Conf. on UAI, pages 203–210, 1996.Google Scholar
  9. 9.
    T. Dean and M. Boddy. An analysis of time-dependent planning. In Proc. AAAI-88, pages 49–54, 1988.Google Scholar
  10. 10.
    T. Dean and M. P. Wellman. Planning and control. Morgan Kaufman Publishers, San Mateo, Ca., 1991.Google Scholar
  11. 11.
    R. Dechter. Bucket elimination: A unifying framework for probabilistic inference. In Proceedings of the Twelfth Conference on Uncertainty in AI, pages 211–219, 1996.Google Scholar
  12. 12.
    D. L. Draper and S. Hanks. Localized partial evaluation of a belief network. In Proc. of UAI-94, pages 170–177, 1994.Google Scholar
  13. 13.
    Jeff Forbes, Tim Huang, Keiji Kanazawa, and Stuart Russell. The batmobile: Towards a bayesian automated taxi. In Proc. of the 14th Int. Joint Conf. on AI (IJCAI'95), pages 1878–1885, 1995.Google Scholar
  14. 14.
    E.J. Horvitz, H.J. Suermondt, and G.F. Cooper. Bounded conditioning: Flexible inference for decisions under scarce resources. In Proc. of the 5th Workshop on Uncertainty in AI, pages 182–193, 1989.Google Scholar
  15. 15.
    Uffe Kjaerulff. Reduction of computation complexity in bayesian networks through removal of weak dependencies. In Proc. of 10th Conf. on UAI, pages 374–382, 1994.Google Scholar
  16. 16.
    S.L. Lauritzen and D.J. Spiegelhalter. Local computations with probabilities on graphical structures and their applications to expert systems. Journal of the Royal Statistical Society, 50(2):157–224, 1988.Google Scholar
  17. 17.
    A.E. Nicholson and N. Jitnah. Belief network algorithms: a study of performance based on domain characterisation. Technical Report 96/249, Department of Computer Science, Monash University, 1996.Google Scholar
  18. 18.
    J. Pearl. Probabilistic Reasoning In Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, 1988.Google Scholar
  19. 19.
    K. L. Poh and E Horvitz. Topological proximity and relevance in graphical decision models. In Proc. of 12th Conf. on UAI, pages 427–435, 1996.Google Scholar
  20. 20.
    M. Wellman and C. Liu. State-space abstraction for anytime evaluation of probabilistic networks. In Proc. of 10th Conf. on UAI, pages 567–574, 1994.Google Scholar
  21. 21.
    N. Zhang and D. Poole. Exploiting causal independence in bayesian network inference. Journal of Artificial Intelligence Research, 5:301–328, 1996.Google Scholar
  22. 22.
    S. Zilberstein. Composition and monitoring of anytime alforithms. In IJCAI 95: Anytime Algorithms and Deliberation Scheduling Workshop, pages 14–21, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • N. Jitnah
    • 1
  • A. Nicholson
    • 1
  1. 1.Department of Computer ScienceMonash UniversityClaytonAustralia

Personalised recommendations