A Bayesian Sampling Algorithm for Evolving Random Hypergraph Models Representing Higher-Order Correlations

고차상관관계를 표현하는 랜덤 하이퍼그래프 모델 진화를 위한 베이지안 샘플링 알고리즘

  • 이시은 (백석대학교 정보통신학부) ;
  • 이인희 (서울대학교 컴퓨터공학부) ;
  • 장병탁 (서울대학교 컴퓨터공학부)
  • Published : 2009.03.15

Abstract

A number of estimation of distribution algorithms have been proposed that do not use explicitly crossover and mutation of traditional genetic algorithms, but estimate the distribution of population for more efficient search. But because it is not easy to discover higher-order correlations of variables, lower-order correlations are estimated most cases under various constraints. In this paper, we propose a new estimation of distribution algorithm that represents higher-order correlations of the data and finds global optimum more efficiently. The proposed algorithm represents the higher-order correlations among variables by building random hypergraph model composed of hyperedges consisting of variables which are expected to be correlated, and generates the next population by Bayesian sampling algorithm Experimental results show that the proposed algorithm can find global optimum and outperforms the simple genetic algorithm and BOA(Bayesian Optimization Algorithm) on decomposable functions with deceptive building blocks.

유전자알고리즘의 교차나 돌연변이 연산을 직접적으로 사용하지 않고 개체군의 확률분포를 추정하여 보다 효율적인 탐색을 수행하려는 분포추정알고리즘이 여러 방법으로 제안되었다. 그러나 실제로 변수들간의 고차상관관계를 파악하는 일은 쉽지 않은 일이라 대부분의 경우 낮은 차수의 상관관계를 제한된 가정하에 추정하게 된다. 본 논문에서는 데이타의 고차상관관계를 표현할 수 있고 최적 해를 좀 더 효율적으로 찾을 수 있는 새로운 분포추정알고리즘을 제안한다. 제안된 알고리즘에서는 상관관계가 있을 것으로 추정되는 변수들의 집합으로 정의된 하이퍼에지로 구성된 랜덤 하이퍼그래프 모델을 구축하여 변수들 간의 고차상관관계를 표현하고, 베이지안 샘플링 알고리즘(Bayesian Sampling Algorithm)을 통해 다음 세대의 개체를 생성한다. 기만하는 빌딩블럭(deceptive building blocks)을 가진 분해가능(decomposable) 함수에 대하여 실험한 결과 성공적으로 최적해를 구할 수 있었으며 단순 유전자알고리즘과 BOA (Bayesian Optimization Algorithm)와 비교하여 좋은 성능을 얻을 수 있었다.

Keywords

References

  1. Muhlenbein, H. & Paass, G., 'From recombination of genes to the estimation of distributions I. Binary parameters,' Parallel Problem Solving from Nature, pp. 178-187, 1996
  2. Larranaga, P., 'A review on estimation of distribution algorithms,' Estimation of Distribution Algoruthms: A New Tools for Evolutionary Computation, Kluwer Academic Publisher, pp. 57-100, 2001
  3. Baluja, S., 'Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning,' Tech. Rep. No.CMU_CS_94_163, Pittsburgh, PA: Carnegie Mellon University, 1994
  4. Harik, G. R., Lobo, F. G., & Goldberg, D. E., 'The compact genetic algorithm,' IlliGAL Report No.97006, Urbana, IL: University Of Illinois at Urbana Champaign, 1997
  5. Pelikan, M., & Muhlenbein, H., 'The bivariate marginal distribution algorithm,' Advances in Soft Computing-Engineering Design and Manufacturing, pp. 521-535, 1999
  6. Pelikan, M., Goldberg, D. E., & Cantu-Paz, E., 'BOA: The Bayesian optimization algorithm,' Genetic and Evolutionary Computation Conference GECCO-99, Vol.1, pp. 525-532, 1999
  7. B.-T. Zhang, 'Random hypergraph models of learning and memory in biomolecular networks: shorter–term adaptability vs longer-term persistency,' IEEE Symposium on Foundations of Computational Intelligence, pp. 344-349, 2007
  8. B.-T. Zhang & J.-K. Kim, 'DNA hypernetworks for information storage and retrieval,' Lecture Notes in Computer Science, DNA12, 4287:298-307, 2006
  9. S. Kim, M.-O. Heo & B.-T. Zhang, 'Text classifier evolved on a simulated DNA computer,' IEEE Congress on Evolutionary Computation(CEC2006), pp. 9196-9202, 2006
  10. C.-H. Park, S.-J. Kim, S. Kim, D.-Y. Cho & B.-T. Zhang, 'Finding cancer related gene combinations using a molecular evolutionary algorithm,' IEEE 7th international conference on Bioinformations & Bioengineering (BIBE2007), pp. 158-163, 2007
  11. B.-T. Zhang, 'Hypernetworks: A molecular evolutionary architecture for cognitive learning and memory,' IEEE Computational Intelligence Magazine, 3(3):49-63, 2008 https://doi.org/10.1109/MCI.2008.926615
  12. Berge, C., Hypergraphs, North-Holland. 1989
  13. B.-T. Zhang, 'A Bayesian framework for evolutionary computation,' IEEE Congress on Evolutionary Computation(CEC1999), pp. 722-728, 1999
  14. B.-T. Zhang, 'A unified Bayesian framework for evolutionary learning and optimization,' Advances in Evolutionary Computing, Springer-Verlag, Chap15, pp. 393-412, 2003
  15. Goldberg, D. E., 'Simple genetic algorithms and the minimal deceptive problem,' Genetic Algorithms and Simulated Annealing, Pitman, pp. 74-88, 1987
  16. Deb, K. & Goldberg, D. E. 'Analyzing deception in trap functions,' Proceedings of Foundations of Genetic Algorithms FOGA-II, pp. 93-108, 1993
  17. Claudio F. Lima, Pelikan, M., Goldberg, D. E., & Fernando G. Lobo, Kumara Sastry, and Mark Hauschild, 'Influence of selection and replacement strategies on linkage learning in BOA.,' IEEE International Conference on Evolutionary Computation (CEC2007), pp. 1083-1090, 2007