Abstract
The rising interest around tractable Probabilistic Graphical Models is due to the guarantees on inference feasibility they provide. Among them, Cutset Networks (CNets) have recently been introduced as models embedding Pearl’s cutset conditioning algorithm in the form of weighted probabilistic model trees with tree-structured models as leaves. Learning the structure of CNets has been tackled as a greedy search leveraging heuristics from decision tree learning. Even if efficient, the learned models are far from being accurate in terms of likelihood. Here, we exploit the decomposable score of CNets to learn their structure and parameters by directly maximizing the likelihood, including the BIC criterion and informative priors on smoothing parameters. In addition, we show how to create mixtures of CNets by adopting a well known bagging method from the discriminative framework as an effective and cheap alternative to the classical EM. We compare our algorithms against the original variants on a set of standard benchmarks for graphical model structure learning, empirically proving our claims.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bach, F.R., Jordan, M.I.: Thin junction trees. In: Advances in Neural Information Processing Systems, vol. 14, pp. 569–576. MIT Press (2001)
Choi, M.J., Tan, V.Y.F., Anandkumar, A., Willsky, A.S.: Learning latent tree graphical models. Journal of Machine Learning Research 12, 1771–1812 (2011)
Chow, C., Liu, C.: Approximating discrete probability distributions with dependence trees. IEEE Transactions on Information Theory 14(3), 462–467 (1968)
Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Machine Learning 29(2–3), 131–163 (1997)
Haaren, J.V., Davis, J.: Markov network structure learning: a randomized feature generation approach. In: Proceedings of the 26th Conference on Artificial Intelligence. AAAI Press (2012)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer (2009)
Heckerman, D., Geiger, D., Chickering, D.: Learning bayesian networks: the combination of knowledge and statistical data. Machine Learning 20, 197–243 (1995)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Lowd, D., Rooshenas, A.: The Libra Toolkit for Probabilistic Models. CoRR abs/1504.00110 (2015)
Lowd, D., Davis, J.: Learning Markov network structure with decision trees. In: Proceedings of the 10th IEEE International Conference on Data Mining, pp. 334–343. IEEE Computer Society Press (2010)
Lowd, D., Domingos, P.: Learning arithmetic circuits. CoRR abs/1206.3271 (2012)
Lowd, D., Rooshenas, A.: Learning Markov networks with arithmetic circuits. In: JMLR Workshop Proceedings of the 16th International Conference on Artificial Intelligence and Statistics, vol. 31, pp. 406–414 (2013)
Meilă, M., Jordan, M.I.: Learning with mixtures of trees. Journal of Machine Learning Research 1, 1–48 (2000)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)
Poon, H., Domingos, P.: Sum-product network: a new deep architecture. In: NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning (2011)
Quinlan, J.R.: Induction of decision trees. Machine Learning Journal 1(1), 81–106 (1986)
Rahman, T., Kothalkar, P., Gogate, V.: Cutset networks: a simple, tractable, and scalable approach for improving the accuracy of chow-liu trees. In: Calders, T., Esposito, F., Hüllermeier, E., Meo, R. (eds.) ECML PKDD 2014, Part II. LNCS, vol. 8725, pp. 630–645. Springer, Heidelberg (2014)
Rooshenas, A., Lowd, D.: Learning sum-product networks with direct and indirect variable interactions. In: JMLR Workshop and Conference Proceedings of the 31st International Conference on Machine Learning, pp. 710–718 (2014)
Roth, D.: On the hardness of approximate reasoning. Artificial Intelligence 82(1–2), 273–302 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Di Mauro, N., Vergari, A., Esposito, F. (2015). Learning Accurate Cutset Networks by Exploiting Decomposability. In: Gavanelli, M., Lamma, E., Riguzzi, F. (eds) AI*IA 2015 Advances in Artificial Intelligence. AI*IA 2015. Lecture Notes in Computer Science(), vol 9336. Springer, Cham. https://doi.org/10.1007/978-3-319-24309-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-24309-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24308-5
Online ISBN: 978-3-319-24309-2
eBook Packages: Computer ScienceComputer Science (R0)