Abstract
Bayesian network (BN) is a probabilistic graphical model which describes the joint probability distribution over a set of random variables. Finding an optimal network structure based on an available training dataset is one of the most important challenges in the field of BNs. Since the problem of searching the optimal BN structure belongs to the class of NP-hard problems, typically greedy algorithms are used to solve it. In this paper two novel learning automata-based algorithms are proposed to solve the BNs’ structure learning problem. In both, there is a learning automaton corresponding with each possible edge to determine the appearance and the direction of that edge in the constructed network; therefore, we have a game of learning automata, at each stage of the proposed algorithms. Two special cases of the game of the learning automata have been discussed, namely, the game with a common payoff and the competitive game. In the former, all the automata in the game receive a unique payoff from the environment, but in the latter, each automaton receives its own payoff. As the algorithms proceed, the learning processes focus on the BN structures with higher scores. The use of learning automata has led to design the algorithms with a guided search scheme, which can avoid getting stuck in local maxima. Experimental results show that the proposed algorithms are capable of finding the optimal structure of BN in an acceptable execution time; and compared with other search-based methods, they outperform them.
Similar content being viewed by others
References
Larranaga P, Poza M, Yarramendi Y, Murga RH, Kuijpers CMH (1996) Learning of Bayesian networks by genetic algorithms: a performance analysis of control parameters. IEEE Trans Pattern Anal Mach Intell 18:912–926
Cheng J, Bell DA, Liu W (1997) An algorithm for Bayesian belief network construction from Data. In: Proceedings of AI & STAT’97, pp 83–90
Larranaga P, Kuijpers CMH, Murga RH, Yurramendi Y (1996) Learning Bayesian network structures by searching for the best ordering with genetic algorithms. IEEE Trans Syst Man Cybern 26:487–493
Myers JW, Laskey KB, Levitt TS (1999) Learning Bayesian networks from incomplete data with stochastic search algorithms. In: UAI Conference, pp 476–485
Rezvani N, Meybodi MR (2009) A learning automata-based technique for training Bayesian networks. In: Proceeding of international conference CACTE, pp 201–212
Tsamardinos I, Brown LE, Aliferis CF (2006) The max-min hill-climbing Bayesian Network structure learning algorithm. Mach Learn 65:31–78
Heckerman D (1995) Learning with Bayesian networks. In: ICML’95
Murphy KP (2001) An introduction to graphical models. Technical Report, Intel Research Technical Report.
Lam W, Bacchus F (1994) Learning Bayesian belief networks: an approach based on the MDL principle. Elsevier Comput Intell 10:269–293
Gallagher M, Wood I, Keith J (2007) Bayesian inference in estimation of distribution algorithms. In: Proceeding of the IEEE congress on evolutionary computation, pp 127–133.
Chickering DM, Geiger D, Heckerman D (1994) Learning Bayesian network is NP-hard. Technical report MSR-TR-94-14
Heckerman D, Geiger D, Chickering DM (2008) A tutorial on learning with Bayesian networks, innovations in Bayesian networks, chapter 3. Springer, Berlin, pp 33–82
Ahn CW, Ramakrishna RS (2008) On the scalability of real-coded Bayesian optimization algorithm. IEEE Trans Evol Comut 12:307–322
Ahn CW, Ramakrishna RS, Goldberg DE (2004) Real-coded Bayesian optimization algorithm: bringing the strength of BOA into the continuous world. Lect Notes Comput Sci 3102:840–851
Heckerman D, Geiger D, Chickering DM (1995) Learning Bayesian networks: the combination of knowledge and statistical data. Technical Report MSR-TR-94-09.
Ahn CW (2006) Advances in evolutionary algorithms: theory, design and practice, studies in computational intelligence. Springer, Berlin
Thathachar MAL, Sastry PS (2002) Varieties of learning automata: an overview. IEEE Trans Syst Man Cybern 32:711–722
Narendra KS, Thathachar MAL (1989) Learning automata: an introduction. Prentice-Hall, Inc., Upper Saddle River
Beigy H, Meybodi MR (2006) A new continuous action-set learning automata for function optimization. J Franklin Inst 343:27
Santharam G, Sastry PS, Thathachar MAL (1994) Continuous action set learning automata for stochastic optimization. J Franklin Inst 331B:607–628
Oommen BJ, Roberts TD (2000) Continuous learning automata solutions to the capacity assignment problem. IEEE Trans Comput 49:608–620
Najim K, Poznyak AS (1994) Learning automata: theory and applications. Pergamon Press, Inc., Elmsford
Obaidat MS, Papadimitriou GI, Pomportsis AS, Laskaridis HS (2002) Learning automata-based bus arbitration for shared-medium ATM switches. IEEE Trans Syst Man Cybern 32:815–820
Papadimitriou GI, Obaidat MS, Pomportsis AS (2002) On the use of learning automata in the control of broad-cast networks: a methodology. IEEE Trans Syst Man Cybern 32:781–790
Beigy H, Meybodi MR (2009) Cellular learning automata based dynamic channel assignment algorithms. Int J Comput Intell Appl 8(3):287–314
Beigy H, Meybodi MR (2006) Utilizing distributed learning automata to solve stochastic shortest path problems. Int J Uncertain Fuzz Knowl Based Syst 14:591–615
Granmo OC, Oommen BJ, Myrer SA, Olsen MG (2007) Learning automata-based solutions to the nonlinear fractional knapsack problem with applications to optimal resource allocation. IEEE Trans Syst Man Cybern 37:166–175
Beigy H, Meybodi MR (2009) Adaptive limited fractional guard channel algorithms a learning automata approach. Int J Uncertain Fuzz Knowl Based Syst 17(6):881–913
Beigy H, Meybodi MR (2009) A learning automata-based algorithm for determination of the number of hidden units for three layer neural networks. Int J Syst Sci 40:101–118
Sastry PS, Nagendra GD, Manwani N (2010) A team of continuous-action learning automata for noisetolerant learning of half-spaces. IEEE Trans Syst Man Cybern 40:19–28
Oommen BJ, Hashem MK (2010) Modeling a student classroom interaction in a tutorial-like system using learning automata. IEEE Trans Syst Man Cybern 40:29–42
Kamil Amir (2003) Graph algorithms CS61B. Spring, UC Berkeley
Sastry PS, Phansalkar VV, Thathachar MAL (1994) Decentralized learning of nash equilibria in multi-person stochastic games with incomplete information. IEEE Trans Syst Man Cybern 24:769–777
Beinlich IA, Suermondt HJ, Chavez RM, Cooper GF (1989) The ALARM monitoring system: a case study with two probabilistic inference techniques for belief networks. In: Proceedings of second european conference on artificial intelligence, pp 247–256
Herskovits EH (1991) Computer Based Probabilistic Network Construction. Doctoral dissertation, Medical Information Sciences, Stanford University.
Campos De, Luis M, Fernandez-Luna JM, Gámez JA, Puerta JM (2002) Ant colony optimization for learning Bayesian networks. Int J Approx Reason 31(3):291–311
Yuan C, Malone B, Wu X (2011) Learning optimal Bayesian networks using A* search. In: IJCAI proceedings-international joint conference on artificial intelligence, vol. 22, no. 3, p 2186.
Singh AP, Moore AW (2005) Finding optimal Bayesian networks by dynamic programming. Technical Report, Carnegie Mellon University
Cussens J, Bartlett M (2013) Advances in Bayesian network learning using integer programming. arXiv preprint arXiv:1309.6825
Jaakkola T, Sontag D, Globerson A, Meila M (2010) Learning Bayesian network structure using LP relaxations. In: Proceedings of the international conference on artificial intelligence and statistics, pp 358–365
Wang XZ, He YL, Wang DD (2014) Non-naive Bayesian classifiers for classification problems with continuous attributes. IEEE Trans Cybern 44(1):21–39
He Yulin, Wang Ran, Kwong Sam, Wang Xizhao (2014) Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis. Inf Sci 259:252–268
Feng G, Zhang JD, Liao SS (2014) A novel method for combining Bayesian networks, theoretical analysis, and its applications. Pattern Recogn 47(5):2057–2069
Murphy PM, Aha DW (1995) UCI repository of machine learning databases. http://www.ics.uci.edu/~mlearn/MLRepository.html
Kohavi R, John G (1997) Wrappers for feature subset selection. Elsevier Sci Artif Intell 97:273–324
Pernkopf F (2005) Bayesian network classifiers versus selective k-NN classifier. Pattern Recogn 38(1):1–10
Author information
Authors and Affiliations
Corresponding author
Appendix A: Experiments implementation
Appendix A: Experiments implementation
In order to evaluate the performance of proposed algorithms and compare them with other algorithms, required programs are implemented with C# on.Net Framework. We have implemented two main elements called DataModel and BayesModel. In DataModel preprocess of datasets is done and an object oriented model is used to maintain the datasets. BayesModel constructs a BN based on a given dataset and then evaluates it. Figures 6 and 7 represent their class diagram.
Rights and permissions
About this article
Cite this article
Gheisari, S., Meybodi, M.R., Dehghan, M. et al. Bayesian network structure training based on a game of learning automata. Int. J. Mach. Learn. & Cyber. 8, 1093–1105 (2017). https://doi.org/10.1007/s13042-015-0476-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-015-0476-9