An Extension of the Infinite Relational Model Incorporating Interaction between Objects

  • Iku Ohama
  • Hiromi Iida
  • Takuya Kida
  • Hiroki Arimura
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7819)


The Infinite Relational Model (IRM) introduced by Kemp et al. (Proc. AAAI2006) is one of the well-known probabilistic generative models for the co-clustering of relational data. The IRM describes the relationship among objects based on a stochastic block structure with infinitely many clusters. Although the IRM is flexible enough to learn a hidden structure with an unknown number of clusters, it sometimes fails to detect the structure if there is a large amount of noise or outliers. To overcome this problem, in this paper we propose an extension of the IRM by introducing a subset mechanism that selects a part of the data according to the interaction among objects. We also present posterior probabilities for running collapsed Gibbs sampling to learn the model from the given data. Finally, we ran experiments on synthetic and real-world datasets, and we showed that the proposed model is superior to the IRM in an environment with noise.


relational data co-clustering generative model subset selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Airoldi, E.M., Blei, D.M., Fienberg, S.E., Xing, E.P.: Mixed membership stochastic blockmodels. J. Mach. Learn. Res. 9, 1981–2014 (2008)zbMATHGoogle Scholar
  2. 2.
    Aldous, D.: Exchangeability and related topics. In: Ecole d’Ete de Probabilities de Saint-Flour XIII, pp. 1–198 (1985)Google Scholar
  3. 3.
    Dhillon, I.S.: Co-clustering documents and words using bipartite spectral graph partitioning. In: Proc. SIGKDD, pp. 269–274 (2001)Google Scholar
  4. 4.
    Dhillon, I.S., Mallela, S., Modha, D.S.: Information-theoretic co-clustering. In: Proc. SIGKDD, pp. 89–98 (2003)Google Scholar
  5. 5.
    Ding, C., Li, T., Peng, W., Park, H.: Orthogonal nonnegative matrix t-factorizations for clustering. In: Proc. SIGKDD, pp. 126–135 (2006)Google Scholar
  6. 6.
    Ferguson, T.S.: A bayesian analysis of some nonparametric problems. The Annals of Statistics 1(2), 209–230 (1973)MathSciNetzbMATHCrossRefGoogle Scholar
  7. 7.
    Fu, W., Song, L., Xing, E.P.: Dynamic mixed membership blockmodel for evolving networks. In: Proc. ICML, pp. 329–336 (2009)Google Scholar
  8. 8.
    Hoff, P.D.: Subset clustering of binary sequences, with an application to genomic abnormality data. Biometrics 61(4), 1027–1036 (2005)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Hubert, L., Arabie, P.: Comparing partitions. J. of Classification 2(1), 193–218 (1985)CrossRefGoogle Scholar
  10. 10.
    Ishiguro, K., Ueda, N., Sawada, H.: Subset infinite relational models. J. Mach. Learn. Res. - Proceedings Track 22, 547–555 (2012)Google Scholar
  11. 11.
    Kemp, C., Tenenbaum, J.B., Griffiths, T.L., Yamada, T., Ueda, N.: Learning systems of concepts with an infinite relational model. In: Proc. AAAI, vol. 1, pp. 381–388 (2006)Google Scholar
  12. 12.
    Liu, J.S.: The collapsed gibbs sampler in bayesian computations with applications to a gene regulation problem. J. Am. Stat. Assoc. 89(427), 958–966 (1994)zbMATHCrossRefGoogle Scholar
  13. 13.
    Mørup, M., Schmidt, M.N., Hansen, L.K.: Infinite multiple membership relational modeling for complex networks. In: Proc. MLSP, pp. 1–6 (2011)Google Scholar
  14. 14.
    Osherson, D.N., Stern, J., Wilkie, O., Stob, M., Smith, E.E.: Default probability. Cognitive Science 15(2), 251–269 (1991)CrossRefGoogle Scholar
  15. 15.
    Roy, D., Kemp, C., Mansinghka, V., Tenenbaum, J.: Learning annotated hierarchies from relational data. In: Proc. NIPS, pp. 1185–1192 (2006)Google Scholar
  16. 16.
    Shafiei, M.M., Milios, E.E.: Latent dirichlet co-clustering. In: Proc. ICDM, pp. 542–551 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Iku Ohama
    • 1
  • Hiromi Iida
    • 1
  • Takuya Kida
    • 2
  • Hiroki Arimura
    • 2
  1. 1.Corporate R&D DivisionPanasonic CorporationOsakaJapan
  2. 2.Division of Computer ScienceHokkaido UniversityHokkaidoJapan

Personalised recommendations