Advertisement

Population Size Extrapolation in Relational Probabilistic Modelling

  • David Poole
  • David Buchman
  • Seyed Mehran Kazemi
  • Kristian Kersting
  • Sriraam Natarajan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8720)

Abstract

When building probabilistic relational models it is often difficult to determine what formulae or factors to include in a model. Different models make quite different predictions about how probabilities are affected by population size. We show some general patterns that hold in some classes of models for all numerical parametrizations. Given a data set, it is often easy to plot the dependence of probabilities on population size, which, together with prior knowledge, can be used to rule out classes of models, where just assessing or fitting numerical parameters will be misleading. In this paper we analyze the dependence on population for relational undirected models (in particular Markov logic networks) and relational directed models (for relational logistic regression). Finally we show how probabilities for real data sets depend on the population size.

Keywords

Bayesian Network Logical Variable Directed Model Weighted Formula Markov Network 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Buntine, W.L.: Operations for learning with graphical models. arXiv preprint cs/9412102 (1994)Google Scholar
  2. 2.
    Domingos, P., Kok, S., Lowd, D., Poon, H., Richardson, M., Singla, P.: Markov logic. In: De Raedt, L., Frasconi, P., Kersting, K., Muggleton, S.H. (eds.) Probabilistic ILP. LNCS (LNAI), vol. 4911, pp. 92–117. Springer, Heidelberg (2008)Google Scholar
  3. 3.
    Friedman, N., Getoor, L., Koller, D., Pfeffer, A.: Learning probabilistic relational models. In: Proc. IJCAI 1999, pp. 1300–1309 (1999)Google Scholar
  4. 4.
    Getoor, L., Taskar, B.: Introduction to Statistical Relational Learning. MIT Press, Cambridge (2007)MATHGoogle Scholar
  5. 5.
    Horsch, M., Poole, D.: A dynamic approach to probabilistic inference using Bayesian networks. In: Proc. Sixth Conference on Uncertainty in AI, pp. 155–161 (1990)Google Scholar
  6. 6.
    Jaeger, M.: Convergence results for relational Bayesian networks. In: Proceedings of LICS 1998 (1998)Google Scholar
  7. 7.
    Jain, D., Barthels, A., Beetz, M.: Adaptive Markov logic networks: Learning statistical relational models with dynamic parameters. In: 9th European Conference on Artificial Intelligence (ECAI), pp. 937–942 (2010)Google Scholar
  8. 8.
    Jain, D., Kirchlechner, B., Beetz, M.: Extending markov logic to model probability distributions in relational domains. In: Hertzberg, J., Beetz, M., Englert, R. (eds.) KI 2007. LNCS (LNAI), vol. 4667, pp. 129–143. Springer, Heidelberg (2007)Google Scholar
  9. 9.
    Kazemi, S.M., Buchman, D., Kersting, K., Natarajan, S., Poole, D.: Relational logistic regression. In: Proc. 14th International Conference on Principles of Knowledge Representation and Reasoning (KR 2014) (2014)Google Scholar
  10. 10.
    Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)Google Scholar
  11. 11.
    Natarajan, S., Khot, T., Lowd, D., Tadepalli, P., Kersting, K., Shavlik, J.: Exploiting causal independence in Markov logic networks: Combining undirected and directed models. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010, Part II. LNCS, vol. 6322, pp. 434–450. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Neville, J., Simsek, O., Jensen, D., Komoroske, J., Palmer, K., Goldberg, H.: Using relational knowledge discovery to prevent securities fraud. In: Proceedings of the 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM Press (2005)Google Scholar
  13. 13.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible inference. Morgan Kaufmann, San Mateo (1988)Google Scholar
  14. 14.
    Perlich, C., Provost, F.: Distribution-based aggregation for relational learning with identifier attributes. Machine Learning 62(1-2), 65–105 (2006)CrossRefGoogle Scholar
  15. 15.
    Poole, D.: First-order probabilistic inference. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI 2003), Acapulco, pp. 985–991 (2003)Google Scholar
  16. 16.
    Poole, D., Buchman, D., Natarajan, S., Kersting, K.: Aggregation and population growth: The relational logistic regression and Markov logic cases. In: UAI 2012 Workshop on Statistical Relational AI (2012)Google Scholar
  17. 17.
    De Raedt, L., Kersting, K.: Probabilistic Inductive Logic Programming: Theory and Applications. In: De Raedt, L., Frasconi, P., Kersting, K., Muggleton, S.H. (eds.) Probabilistic Inductive Logic Programming. LNCS (LNAI), vol. 4911, pp. 1–27. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  18. 18.
    Richardson, M., Domingos, P.: Markov logic networks. Machine Learning 42, 107–136 (2006)CrossRefGoogle Scholar
  19. 19.
    de Salvo Braz, R., Amir, E., Roth, D.: Lifted first-order probabilistic inference. In: Getoor, L., Taskar, B. (eds.) Introduction to Statistical Relational Learning. MIT Press (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • David Poole
    • 1
  • David Buchman
    • 1
  • Seyed Mehran Kazemi
    • 1
  • Kristian Kersting
    • 2
  • Sriraam Natarajan
    • 3
  1. 1.University of British ColumbiaCanada
  2. 2.Technical University of DortmundGermany
  3. 3.Indiana UniversityUSA

Personalised recommendations