Structure Learning with Nonparametric Decomposable Models

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4668)


We present a novel approach to structure learning for graphical models. By using nonparametric estimates to model clique densities in decomposable models, both discrete and continuous distributions can be handled in a unified framework. Also, consistency of the underlying probabilistic model is guaranteed. Model selection is based on predictive assessment, with efficient algorithms that allow fast greedy forward and backward selection within the class of decomposable models. We show the validity of this structure learning approach on toy data, and on two large sets of gene expression data.


Model Score Structure Learning Chordal Graph Nonparametric Density Estimate Clique Tree 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lauritzen, S.L.: Graphical Models. Oxford Statistical Science Series, vol. 17. Clarendon Press, Oxford (1996)Google Scholar
  2. 2.
    Cowell, R.G., Dawid, A.P., Lauritzen, S.L., Spiegelhalter, D.J.: Probabilistic Networks and Expert Systems. In: Statistics for Engineering and Information Science, Springer, Heidelberg (1999)Google Scholar
  3. 3.
    Heckerman, D.: A tutorial on learning with Bayesian networks. In: Jordan, M.I. (ed.) Learning in Graphical Models, MIT Press, Cambridge (1998)Google Scholar
  4. 4.
    Song, Y., Goncalves, L., Perona, P.: Unsupervised learning of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(7), 814–827 (2003)CrossRefGoogle Scholar
  5. 5.
    Banerjee, O., El Ghaoui, L., d’Aspremont, A., Natsoulis, G.: Convex optimization techniques for fitting sparse gaussian graphical models. In: De Raedt, L., Wrobel, S. (eds.) Proceedings of ICML06, pp. 89–96. ACM Press, New York (2006)Google Scholar
  6. 6.
    Hofmann, R., Tresp, V.: Nonlinear Markov networks for continuous variable. In: Jordan, M.I., Kearns, M.J., Solla, S.A. (eds.) Advances in Neural Information Processing Systems, vol. 10, MIT Press, Cambridge (1998)Google Scholar
  7. 7.
    Friedman, N., Nachman, I.: Gaussian process networks. In: Proceedings of UAI 2000, pp. 211–219. Morgan Kaufmann, San Francisco (2000)Google Scholar
  8. 8.
    Friedman, N., Linial, M., Nachman, I., Pe’er, D.: Using bayesian networks to analyze expression data. Journal of Computational Biology 7, 601–620 (2000)CrossRefGoogle Scholar
  9. 9.
    Hartwell, L.H., Hopfield, J.J., Leibler, S., Murray, A.W.: From molecular to modular cell biology. Nature 402, C47 (1999)CrossRefGoogle Scholar
  10. 10.
    Bouckaert, R.R.: Properties of Bayesian belief network learning algorithms. In: de Mantaras, R.L., Poole, D.L. (eds.) Proceedings of UAI 94, pp. 102–109. Morgan Kaufmann, San Francisco (1994)Google Scholar
  11. 11.
    de Campos, L.M.: Characterizations of decomposable dependency models. Journal of Artificial Intelligence Research 5, 289–300 (1996)Google Scholar
  12. 12.
    Giudici, P., Green, P.J.: Decomposable graphical Gaussian model determination. Biometrika 86, 785–801 (1999)zbMATHCrossRefGoogle Scholar
  13. 13.
    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. In: Monographs on Statistics and Applied Probability, vol. 26, Chapman & Hall, Sydney, Australia (1986)Google Scholar
  14. 14.
    Deshpande, A., Garofalakis, M., Jordan, M.I.: Efficient stepwise selection in decomposable models. In: Breese, J., Koller, D. (eds.) Proceedings of UAI 2001, Morgan Kaufmann, San Francisco (2001)Google Scholar
  15. 15.
    Ibarra, L.: Fully dynamic algorithms for chordal graphs and split graphs. Technical Report DCS-262-IR. Department of Computer Science, University of Victoria, CA (2000)Google Scholar
  16. 16.
    Sleator, D.D., Tarjan, R.E.: Self-adjusting binary search trees. Journal of the ACM 32(3), 652–686 (1985)zbMATHCrossRefGoogle Scholar
  17. 17.
    Yeoh, E.J., et al.: Classification, subtype discovery, and prediction of outcome in pediatric acute lymphoblastic leukemia by gene expression profiling. Cancer Cell 1(2), 133–143 (2002)CrossRefGoogle Scholar
  18. 18.
    Dejori, M., Schwaighofer, A., Tresp, V., Stetter, M.: Mining functional modules in genetic networks with decomposable graphical models. OMICS A Journal of Integrative Biology 8(2), 176–188 (2004)CrossRefGoogle Scholar
  19. 19.
    Spira, A., Beane, J., Shah, V., Liu, G., Schembri, F., Yang, X., Palma, J., Brody, J.S.: Effects of cigarette smoke on the human airway epithelial cell transcriptome. Proceedings of the National Academy of Sciences of the United States of America 101(27), 10143–10148 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  1. 1.Fraunhofer FIRST, Intelligent Data Analysis Group, Kekulestr. 7, 12489 BerlinGermany
  2. 2.Siemens Corporate Technology, 81730 MunichGermany

Personalised recommendations