Bayesian Network Structure Learning from Limited Datasets through Graph Evolution

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Alberto Paolo Tonda and Evelyne Lutton and 
                 Romain Reuillon and Giovanni Squillero and 
                 Pierre-Henri Wuillemin",
  title =        "Bayesian Network Structure Learning from Limited
                 Datasets through Graph Evolution",
  booktitle =    "Proceedings of the 15th European Conference on Genetic
                 Programming, EuroGP 2012",
  year =         "2012",
  month =        "11-13 " # apr,
  editor =       "Alberto Moraglio and Sara Silva and 
                 Krzysztof Krawiec and Penousal Machado and Carlos Cotta",
  series =       "LNCS",
  volume =       "7244",
  publisher =    "Springer Verlag",
  address =      "Malaga, Spain",
  pages =        "254--265",
  organisation = "EvoStar",
  isbn13 =       "978-3-642-29138-8",
  DOI =          "doi:10.1007/978-3-642-29139-5_22",
  keywords =     "genetic algorithms, genetic programming, Evolutionary
                 computation, Bayesian network structure learning,
                 Bayesian networks, Graph representation",
  abstract =     "Bayesian networks are stochastic models, widely
                 adopted to encode knowledge in several fields. One of
                 the most interesting features of a Bayesian network is
                 the possibility of learning its structure from a set of
                 data, and subsequently use the resulting model to
                 perform new predictions. Structure learning for such
                 models is a NP-hard problem, for which the scientific
                 community developed two main approaches:
                 score-and-search metaheuristics, often
                 evolutionary-based, and dependency-analysis
                 deterministic algorithms, based on stochastic tests.
                 State-of-the-art solutions have been presented in both
                 domains, but all methodologies start from the
                 assumption of having access to large sets of learning
                 data available, often numbering thousands of samples.
                 This is not the case for many real-world applications,
                 especially in the food processing and research
                 industry. This paper proposes an evolutionary approach
                 to the Bayesian structure learning problem,
                 specifically tailored for learning sets of limited
                 size. Falling in the category of score-and-search
                 techniques, the methodology exploits an evolutionary
                 algorithm able to work directly on graph structures,
                 previously used for assembly language generation, and a
                 scoring function based on the Akaike Information
                 Criterion, a well-studied metric of stochastic model
                 performance. Experimental results show that the
                 approach is able to outperform a state-of-the-art
                 dependency-analysis algorithm, providing better models
                 for small datasets.",
  notes =        "Part of \cite{Moraglio:2012:GP} EuroGP'2012 held in
                 conjunction with EvoCOP2012 EvoBIO2012, EvoMusArt2012
                 and EvoApplications2012",

Genetic Programming entries for Alberto Tonda Evelyne Lutton Romain Reuillon Giovanni Squillero Pierre-Henri Wuillemin