Abstract
In this work we consider the problem of learning the structure of Markov networks from data. We present an approach for tackling this problem called IBMAP, together with an efficient instantiation of the approach: the IBMAP-HC algorithm, designed for avoiding important limitations of existing independence-based algorithms. These algorithms proceed by performing statistical independence tests on data, trusting completely the outcome of each test. In practice tests may be incorrect, resulting in potential cascading errors and the consequent reduction in the quality of the structures learned. IBMAP contemplates this uncertainty in the outcome of the tests through a probabilistic maximum-a-posteriori approach. The approach is instantiated in the IBMAP-HC algorithm, a structure selection strategy that performs a polynomial heuristic local search in the space of possible structures. We present an extensive empirical evaluation on synthetic and real data, showing that our algorithm outperforms significantly the current independence-based algorithms, in terms of data efficiency and quality of learned structures, with equivalent computational complexities. We also show the performance of IBMAP-HC in a real-world application of knowledge discovery: EDAs, which are evolutionary algorithms that use structure learning on each generation for modeling the distribution of populations. The experiments show that when IBMAP-HC is used to learn the structure, EDAs improve the convergence to the optimum.
Similar content being viewed by others
References
Asuncion, A., Newman, D.J.: UCI machine learning repository (2007)
Agresti, A.: Categorical Data Analysis, 2nd edn. Wiley (2002)
Alden, M.: MARLEDA: Effective Distribution Estimation Through Markov Random Fields. Ph.D. thesis, Dept of CS University of Texas Austin (2007)
Aliferis, C., Statnikov, A., Tsamardinos, I., Mani, S., Koutsoukos, X.: Local Causal and Markov Blanket induction for causal discovery and feature selection for classification part i: algorithms and empirical evaluation. JMLR 11, 171–234 (2010)
Aliferis, C., Statnikov, A., Tsamardinos, I., Mani, S., Koutsoukos, X.: Local causal and Markov blanket induction for causal discovery and feature selection for classification part ii: analysis and extensions. JMLR 11, 235–284 (2010)
Aliferis, C., Tsamardinos, I., Statnikov, A.: HITON, a novel Markov blanket algorithm for optimal variable selection. AMIA Fall (2003)
Bromberg, F., Margaritis, D.: Improving the reliability of causal discovery from small data sets using argumentation. JMLR 10, 301–340 (2009)
Bromberg, F., Margaritis, D., Honavar, V.: Efficient markov network structure discovery using independence tests. In: Proc SIAM Data Mining, p. 06 (2006)
Bromberg, F., Margaritis, D., Honavar, V.: Efficient Markov network structure discovery using independence tests. JAIR 35, 449–485 (2009)
Chickering, D.M.: Learning Bayesian networks is NP-Complete. In: Fisher, D., Lenz, H. (eds.) Learning from Data: Artificial Intelligence and Statistics V, pp. 121–130. Springer, Berlin (1996)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley-Interscience, New York (1991)
Davis, J., Domingos, P.: Bottom-up learning of Markov network structure. In: ICML, pp. 271–278 (2010)
Della Pietra, S., Della Pietra, V.J., Lafferty, J.D.: Inducing features of random fields. IEEE Trans. PAMI 19(4), 380–393 (1997)
Friedman, N., Linial, M., Nachman, I., Pe’er, D.: Using Bayesian networks to analyze expression data. J. Comput. Biol., 601–620 (2000)
Ganapathi, V., Vickrey, D., Duchi, J., Koller, D.: Constrained approximate maximum entropy learning of Markov random fields. In: Uncertainty in Artificial Intelligence, pp. 196–203 (2008)
Hammersley, J.M., Clifford, P.: Markov fields on finite graphs and lattices (1968)
Hettich, S., Bay, S.D. The UCI KDD archive (1999)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Larraṅaga, P., Lozano, J.A.: Estimation of Distribution Algorithms. A New Tool for Evolutionary Computation. Kluwer, Norwell (2002)
Lauritzen, S.L.: Graphical Models. Oxford University Press, New York (1996)
Lee, S.I., Ganapathi, V., Koller, D.: Efficient structure learning of Markov networks using L1-regularization. NIPS (2006)
Li, S.: Markov Random Field Modeling in Image Analysis. Springer (2009)
Margaritis, D.: Distribution-free learning of Bayesian network structure in continuous domains. In: Proceedings of AAAI (2005)
Margaritis, D., Bromberg, F.: Efficient Markov network discovery using particle filter. Comput. Intell. 25(4), 367–394 (2009)
Margaritis, D., Thrun, S.: Bayesian network induction via local neighborhoods. In: Proceedings of NIPS06 (2000)
McCallum, A.: Efficiently inducing features of conditional random fields. In: Proceedings of Uncertainty in Artificial Intelligence (UAI) (2003)
Minka, T.: Divergence measures and message passing. Tech. rep. Microsoft Research (2005)
Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1998)
Mühlenbein, H., Paaß, G.: From recombination of genes to the estimation of distributions I. Binary parameters. In: Voigt, H.M., Ebeling,W., Rechenberg, I., Schwefel, H.P. (eds.) Parallel Problem Solving from NaturePPSN IV. Lecture Notes in Computer Science, vol. 1141, pp. 178187. Springer, Berlin (1996). doi:10.1007/3-540-61723-X982
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)
Ravikumar, P., Wainwright, M.J., Lafferty, J.D.: High-dimensional Ising model selection using L1-regularized logistic regression. Ann. Stat. 38, 1287–1319 (2010). doi:10.1214/09-AOS691
Santana, R.: Estimation of distribution algorithms with kikuchi approximations. Evol. Comput. 13(1), 67–97 (2005). doi:10.1162/1063656053583496
Schlüter, F.: A survey on independence-based markov networks learning. Artif. Intell. Rev., 1–25 (2012). doi:10.1007/s10462-012-9346-y
Shakya, S., McCall, J.: Optimization by estimation of distribution with deum framework based on Markov random fields. Int. J. Autom. Comput. 4(3), 262272. http://www.springerlink.com/index/10.1007/s11633-007-0262-6 (2007)
Shakya, S., Santana, R., Lozano, J.A.: A markovianity based optimisation algorithm. Genet. Program Evolvable Mach. 13(2), 159–195 (2012)
Schmidt, M., Murphy, K., Fung, G., Rosales, R.: Structure learning in random fields for heart motion abnormality detection. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1–18. CVPR (2008). doi:http://www.cs.ubc.ca/~murphyk/Papers/cvpr08.pdf
Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search. Adaptive Computation and Machine Learning Series. MIT Press, Cambridge (2000)
Van Haaren, J., Davis, J.: Markov network structure learning: a randomized feature generation approach. In: Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence. https://lirias.kuleuven.be/handle/123456789/345604 (2012)
Van Haaren, J., Davis, J., Lappenschaar, M., Hommersom, A.: Exploring disease interactions using Markov networks. In: Proceedings of the AAAI-2013 (HIAI-2013). Bellevue, Washington, 15 July (2013)
Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Found. Trends Mach. Learn. 1(1–2), 1–305 (2008)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Schlüter, F., Bromberg, F. & Edera, A. The IBMAP approach for Markov network structure learning. Ann Math Artif Intell 72, 197–223 (2014). https://doi.org/10.1007/s10472-014-9419-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10472-014-9419-5