Abstract
We propose a method to estimate the graph structure from data for a Markov random field (MRF) model. The method is valuable in many practical situations where the true topology is uncertain. First the similarities of the MRF variables are estimated by applying methods from information theory. Then, employing multidimensional scaling on the dissimilarity matrix obtained leads to a 2D topology estimate of the system. Finally, applying uniform thresholding on the node distances in the topology estimate gives the neighbourhood relations of the variables, hence defining the MRF graph estimate. Conditional independence properties of a MRF model are defined by the graph topology estimate thus enabling the estimation of the MRF model parameters e.g. through the pseudolikelihood estimation scheme. The proposed method is demonstrated by identifying MRF model for a telecommunications network, which can be used e.g. in analysing the effects of stochastic disturbances to the network state.
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
Besag, J.E.: Statistical analysis of non-lattice data. The Statistician 24(3), 179–195 (1975)
Bishop, C.M.: Pattern Recognition and Machine Learning, pp. 383–393. Springer, Heidelberg (2006)
Cover, T.M., Thomas, J.A.: Elements of Information Theory, pp. 5–21. John Wiley & Sons, Chichester (1991)
Cressie, N.A.C.: Statistics for Spatial Data, pp. 383–573. John Wiley & Sons, Inc, Chichester (1993)
Everitt, B., Rabe-Hesketh, S.: Kendall’s Library of Statistics 4. The Analysis of Proximity Data. Arnold, 11–68 (1997)
Friedman, N., Koller, D.: Being Bayesian about Network Structure: A Bayesian Approach to Structure Discovery in Bayesian Networks. Machine Learning 50, 95–126 (2003)
Kruskal, J.B.: Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika 29, 1–27 (1964)
Kruskal, J.B.: Nonmetric multidimensional scaling: A numerical method. Psychometrika 29, 115–129 (1964)
Kullback, S.: Information Theory and Statistics. John Wiley (1959); reprinted by Dover Publications, Inc. pp. 155–188 (1997)
MacKay, D.: Information Theory, Inference and Learning Algorithms, pp. 357–421. Cambridge Univ. Press, Cambridge (2003)
Press, W., et al.: Numerical Recipes: The Art of Scientific Computation, pp. 476–481. Cambridge Univ. Press, Cambridge (1986)
Rajala, M., Ritala, R.: Mutual Information and Multidimensional Scaling as Means to Reconstruct Network Topology. In: Proc. SICE-ICCAS pp. 1398–1403 (2006)
Rajala, M., Ritala, R.: Statistical Model Describing Networked Systems Phenomena. In: Proc. IEEE Symp. on Comp. and Comm., pp. 647–654. IEEE Computer Society Press, Los Alamitos (2006)
Rue, H., Held, L.: Gaussian Markov Random Fields: Theory and Applications, pp. 15–83. Chapman&Hall/CRC (2005)
Schroeder, D.V.: An Introduction to Thermal Physics, pp. 220–256. Addison-Wesley, London, UK (1999)
Stuart, A., Ord, K., Arnold, S.: Kendall’s Advanced Theory of Statistics. In: Classical Inference & the Linear Model, 6th edn., vol. 2A, pp. 46–116. Oxford Univ. Press, Oxford, UK (1999)
Steyvers, M.: Multidimensional Scaling. In: Encyclopedia of Cognitive Science, Macmillan, London (2002)
Winkler, G.: Image Analysis, Random Fields and Markov Chain Monte Carlo Methods. Springer, Heidelberg (2003)
Yang, C.N.: The Spontaneous Magnetization of a Two-Dimensional Ising Model. Physical Review 85(5), 808–816 (1952)
Yeomans, J.M.: Statistical Mechanics of Phase Transitions. Oxford University Press, Oxford, UK (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rajala, M., Ritala, R. (2007). A Method to Estimate the Graph Structure for a Large MRF Model. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74695-9_86
Download citation
DOI: https://doi.org/10.1007/978-3-540-74695-9_86
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74693-5
Online ISBN: 978-3-540-74695-9
eBook Packages: Computer ScienceComputer Science (R0)