A New BN Structure Learning Mechanism Based on Decomposability of Scoring Functions

Bayesian networks are a powerful approach for representing and reasoning under conditions of uncertainty. Many researchers aim to find good algorithms for learning Bayesian networks from data. And the bio-inspired search algorithm is one of the most effective algorithms. We proposed a hybrid algorithm called MIC-BPSO (Maximal Information Coefficient – Binary Particle Swarm Optimization). This algorithm firstly applies network construction method based on Maximal Information Coefficient to improve the quality of initial particles, and then uses the decomposability of scoring function to modify BPSO algorithm. Experiment results show that, without a given node ordering, this algorithm outperforms MI-BPSO, I-BN-PSO, MWST-HC and K2 algorithm.

[1]  Chunnian Liu,et al.  An artificial bee colony algorithm for learning Bayesian networks , 2012, Soft Computing.

[2]  Mauro Birattari,et al.  Swarm Intelligence , 2012, Lecture Notes in Computer Science.

[3]  Evelyne Lutton,et al.  Bayesian network structure learning using cooperative coevolution , 2009, GECCO.

[4]  Wensheng Zhang,et al.  Improved heuristic equivalent search algorithm based on Maximal Information Coefficient for Bayesian Network Structure Learning , 2013, Neurocomputing.

[5]  Michael Mitzenmacher,et al.  Detecting Novel Associations in Large Data Sets , 2011, Science.

[6]  Chen Xiao,et al.  A binary particle swarm optimization algorithm inspired by multi-level organizational learning behavior , 2012, Eur. J. Oper. Res..

[7]  Chunnian Liu,et al.  A hybrid method for learning Bayesian networks based on ant colony optimization , 2011, Appl. Soft Comput..

[8]  Kevin Kontos,et al.  Information-Theoretic Inference of Large Transcriptional Regulatory Networks , 2007, EURASIP J. Bioinform. Syst. Biol..

[9]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[10]  Author.  A Memetic Approach to Bayesian Network Structure Learning , 2012 .

[11]  Yinghua Zhang,et al.  A novel Bayesian network structure learning algorithm based on Maximal Information Coefficient , 2012, 2012 IEEE Fifth International Conference on Advanced Computational Intelligence (ICACI).

[12]  Concha Bielza,et al.  A review on evolutionary algorithms in Bayesian network learning and inference tasks , 2013, Inf. Sci..

[13]  H. Cardot,et al.  Evolutionary Methods for Learning Bayesian Network Structures , 2008 .

[14]  Julie Cowie,et al.  Particle Swarm Optimisation for learning Bayesian Networks , 2007, World Congress on Engineering.

[15]  Michael L. Bittner,et al.  A Robust Structural PGN Model for Control of Cell-Cycle Progression Stabilized by Negative Feedbacks , 2007, EURASIP J. Bioinform. Syst. Biol..

[16]  Guoliang Li,et al.  DBN structure learning based on MI-BPSO algorithm , 2014, 2014 IEEE/ACIS 13th International Conference on Computer and Information Science (ICIS).

[17]  Pin Luarn,et al.  A discrete version of particle swarm optimization for flowshop scheduling problems , 2007, Comput. Oper. Res..

[18]  于海斌,et al.  A hybrid PSO-GD based intelligent method for machine diagnosis , 2006 .

[19]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .

[20]  John A. W. McCall,et al.  Two novel Ant Colony Optimization approaches for Bayesian network structure learning , 2010, IEEE Congress on Evolutionary Computation.

[21]  Thomas A. Runkler,et al.  Using a Local Discovery Ant Algorithm for Bayesian Network Structure Learning , 2009, IEEE Transactions on Evolutionary Computation.

[22]  Hubert Cardot,et al.  Two evolutionary methods for learning Bayesian network structures , 2006, 2006 International Conference on Computational Intelligence and Security.