Abstract
Multiply Sectioned Bayesian Networks(MSBNs) extend the junction tree based inference algorithms into a coherent framework for flexible modelling and effective inference in large domains. However,these junction tree based algorithms are limited by the need to maintain an exact representation of clique potentials. This paper presents a new unified inference framework for MSBNs that combines approximate inference algorithms and junction tree based inference algorithms, thereby circumvents this limitation. As a result our algorithm allow inference in much larger domains given the same computational resources. We believe it is the very first approximate inference algorithm for MSBNs.
This work is supported by NSF of china grant 79990580 and National 973 Fundamental Research Program grant G1998030414. Thanks the anonymous reviewers for helpful comments.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dawid, A. P. Kjaerulff, U. Lauritzen, S.L. (1994). Hybrid propagation in junction trees, proceedings of the Fifth international conference on information processing and management of uncertainty in Knowledge-based systems (IPMU).
Kjaerulff, U. HUGS: Combining Exact Inference and Gibbs Sampling in Junction Trees, In proc. UAI,1995.
Daphne Koller, Uri Lerner, Dragomir Angelov. A General Algorithm for Approximate Inference and Its application to Hybrid Bayes Nets. In proc. UAI, 1999.
Y. Xiang. Belief updating in multiply sectioned Bayesian networks without repeated local propagations. International Journal of Approximate Reasoning 23 (2000).
G. Shafer. Probabilistic Expert Systems. Society for Industrial and Applied Mathematics Philadelphia, 1996.
F.V. Jensen. An introduction to Bayesian networks, UCL Press, 1996.
F.V. Jensen. S.L. Lauritzen, K.G. Olesen, Bayesian updating in causal probabilistic networks by local computations, Computational Statistics Quarterly 4 (1990).
S.L. Lauritzen, D.J. Spiegelhalter. Local computation with probabilities on graphical structures and their application to expert systems, Journal of Royal Statistical Society B 50( 1988).
A.L. Madsen, F.V. Jensen. Lazy propagation in junction trees, in: Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, 1998.
Y. Xiang. Optimization of inter-subnet belief updating in multiply sectioned Bayesian networks, In proc. UAI,1995.
Y. Xiang. A probabilistic framework for cooperative multi-agent distributed interpretation and optimization of communication, Artificial Intelligence 87 (1/2) (1996).
Y. Xiang and F.V. Jensen. Inference in Multiply Sectioned Bayesian Networks with Extended Shafer-Shenoy and Lazy Propagation, In proc. UAI,1999.
Y. Xiang, D. Poole, M.P. Beddoes. Multiply sectioned Bayesian networks and junction forests for large knowledge based systems, Computational Intelligence 9 (2) (1993).
Dagum P, Luby M. An optimal Approximation for Bayesian inference. Artificial Intelligence 1993, 60: 141–153.
Neal R M. Probabilistic inference using Markov chain Monte Carlo methods: [Technical Report CRGTR-93-1], Department of computer Science, university of Toronto, 1993.
J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann, Los Altos, CA, 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hongwei, Z., Fengzhan, T., Yuchang, L. (2001). General Algorithm for Approximate Inference in Multiply Sectioned Bayesian Networks. In: Hoffmann, F., Hand, D.J., Adams, N., Fisher, D., Guimaraes, G. (eds) Advances in Intelligent Data Analysis. IDA 2001. Lecture Notes in Computer Science, vol 2189. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44816-0_33
Download citation
DOI: https://doi.org/10.1007/3-540-44816-0_33
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42581-6
Online ISBN: 978-3-540-44816-7
eBook Packages: Springer Book Archive