Advertisement

Bayesian Methods for Graph Clustering

  • Pierre LatoucheEmail author
  • Etienne Birmelé
  • Christophe Ambroise
Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

Networks are used in many scientific fields such as biology, social science, and information technology. They aim at modelling, with edges, the way objects of interest, represented by vertices, are related to each other. Looking for clusters of vertices, also called communities or modules, has appeared to be a powerful approach for capturing the underlying structure of a network. In this context, the Block-Clustering model has been applied on random graphs. The principle of this method is to assume that given the latent structure of a graph, the edges are independent and generated from a parametric distribution. Many EM-like strategies have been proposed, in a frequentist setting, to optimize the parameters of the model. Moreover, a criterion, based on an asymptotic approximation of the Integrated Classification Likelihood (ICL), has recently been derived to estimate the number of classes in the latent structure. In this paper, we show how the Block-Clustering model can be described in a full Bayesian framework and how the posterior distribution, of all the parameters and latent variables, can be approximated efficiently applying Variational Bayes (VB). We also propose a new non-asymptotic Bayesian model selection criterion. Using simulated data sets, we compare our approach to other strategies. We show that our criterion can outperform ICL.

Keywords

Bayesian model selection Block-clustering model Integrated classification likelihood Random graphs Variational Bayes Variational EM 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Attias, H. (1999). Inferring parameters and structure of latent variable models by variational bayes. In K. B. Laskey, & H. Prade (Eds.), Uncertainty in artificial intelligence: Proceedings of the fifth conference (pp. 21–30). San Fransisco, CA: Morgan Kaufmann.Google Scholar
  2. Biernacki, C., Celeux, G., & Govaert, G. (2000). Assessing a mixture model for clustering with the integrated completed likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7, 719–725.CrossRefGoogle Scholar
  3. Bishop, C. M. (2006). Pattern recognition and machine learning. Berlin: Springer.zbMATHGoogle Scholar
  4. Corduneanu, A., & Bishop, C. M. (2001). Variational bayesian model selection for mixture distributions. In T. Richardson, & T. Jaakkola (Eds.), Proceedings eighth international conference on artificial intelligence and statistics (pp. 27–34). San Fransisco, CA: Morgan Kaufmann.Google Scholar
  5. Daudin, J., Picard, F., & Robin, S. (2008). A mixture model for random graph. Statistics and Computing, 18, 1–36.CrossRefMathSciNetGoogle Scholar
  6. Hofman, J. M., & Wiggins, C. H. (2008). A bayesian approach to network modularity. Physical Review Letters, 100, 258701.CrossRefGoogle Scholar
  7. Hubert, L., & Arabie, P. (1985). Comparing partitions. Journal of Classification, 2, 193–218.CrossRefGoogle Scholar
  8. Latouche, P., Birmelé, E., & Ambroise. C. (2008). Bayesian methods for graph clustering. Technical report, SSB.Google Scholar
  9. MacKay, D. (1992). A practical bayesian framework for backpropagation networks. Neural Computation, 4, 448–472.CrossRefGoogle Scholar
  10. Mariadassou, M., & Robin, S. (2007). Uncovering latent structure in networks. Technical report, INRA, SSB.Google Scholar
  11. Ng, A. Y., Jordan, M. I., & Weiss, Y. (2001). On spectral clustering: Analysis and an algorithm. Advances in Neural Information Processing Systems, 14.Google Scholar
  12. Parisi, G. (1988). Statistical field theory. Reading MA: Addison Wesley.zbMATHGoogle Scholar
  13. Snijders, T. A. B., & Nowicki, K. (1997). Estimation and prediction for stochastic block-structures for graphs with latent block sturcture. Journal of Classification, 14, 75–100.zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Pierre Latouche
    • 1
    Email author
  • Etienne Birmelé
  • Christophe Ambroise
  1. 1.Laboratoire Statistique et Génome, UMR CNRS 8071-INRA 1152-UEVEEvryFrance

Personalised recommendations