Statistics and Computing

, Volume 14, Issue 3, pp 181–198 | Cite as

Node deletion sequences in influence diagrams using genetic algorithms

  • M. Gómez
  • C. Bielza


Influence diagrams are powerful tools for representing and solving complex inference and decision-making problems under uncertainty. They are directed acyclic graphs with nodes and arcs that have a precise meaning. The algorithm for evaluating an influence diagram deletes nodes from the graph in a particular order given by the position of each node and its arcs with respect to the value node. In many cases, however, there is more than one possible node deletion sequence. They all lead to the optimal solution of the problem, but may involve different computational efforts, which is a primary issue when facing real-size models. Finding the optimal deletion sequence is a NP-hard problem. The proposals given in the literature have proven to require complex transformations of the influence diagram. In this paper, we present a genetic algorithm-based approach, which merely has to be added to the influence diagram evaluation algorithm we use, and whose codification is straightforward. The experiments, varying parameters like crossover and mutation operators, population sizes and mutation rates, are analysed statistically, showing favourable results over existing heuristics.

decision-making under uncertainty influence diagrams genetic algorithms NP-hard problems node deletion sequence statistical analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Alander J.T. 1992. On optimal population size of genetic algorithms. In: Proc. CompEuro 1992, Comput. Sys. and Soft. Engineer., 6th Annual European Computer Conf., pp. 65-70.Google Scholar
  2. Amir E. 2001. Efficient approximation for triangulation of minimum treewidth, In: Koller D. and Breese J. (Eds.), Proc. 17th Conf. on Uncertainty in Artificial Intelligence, San Francisco, CA, Morgan Kaufmann, pp. 7-15.Google Scholar
  3. Arnborg S., Corneil D., and Proskurowski, A. 1987. Complexity of finding embeddings in a k-tree. SIAM Journal Algebraic Discrete Methods 8:277-284.Google Scholar
  4. Bielza C., Gómez M., RRíos-Insua S., and Fernández del Pozo J.A. 2000. Structural, elicitation and computational issues faced when solving complex decision problems with influence diagrams. Computers and Operations Research 27(7/8):725-740.Google Scholar
  5. Bielza C. and Shenoy P.P. 1999. A comparison of graphical techniques for asymmetric decision problems. Management Science 45(11): 1552-1569.Google Scholar
  6. Cano A. and Moral S. 1994. Heuristic algorithms for the triangulation of graphs. In: Proc. 5th Int. Conf. on Information Processing and Management of Uncertainty in Knowledge Based Systems (IPMU), Vol. 1, pp. 166-171.Google Scholar
  7. Chew E.P., Ong C.J., and Lim K.H. 2002. Variable period adaptive genetic algorithm. Computers & Industrial Engineering 42(2-4):353-360.Google Scholar
  8. Clemen R.T. 1996. Making Hard Decisions: An Introduction to Decision Analysis, 2nd edition. Duxbury, Belmont, CA.Google Scholar
  9. Cooper G.F. 1988. A method for using belief networks as influence diagrams. In: Proc. Workshop on Uncertainty in Artificial Intelligence, Minneapolis, Minnesota, pp. 55-63.Google Scholar
  10. Cooper G.F. 1990. The computational complexity of probabilistic inference using Bayesian belief networks. Artificial Intelligence 42:393-405.Google Scholar
  11. De Jong K.A. 1975. An analysis of the behavior of a class of genetic adaptive systems. PhD. Diss., University of Michigan.Google Scholar
  12. Ezawa K.J. 1986. Efficient evaluation of influence diagrams. PhD. Diss., Dept. of Engineering-Economic Systems, Stanford University, Stanford, CA.Google Scholar
  13. Fogarty T.C. 1989.Varying the probability of mutation in the genetic algorithm. In: Proc. Third Int. Conf. on Genetic Algorithms, pp. 104-109.Google Scholar
  14. Gómez. M. 2002. IctNeo: A decision support system for neonatal jaundice treatment. PhD. Diss., Dept. of Artificial Intelligence, Technical University of Madrid, Spain.Google Scholar
  15. Henrion M. 1989. Some practical issues in constructing belief networks. Uncertainty in Artificial Intelligence 3:161-173.Google Scholar
  16. Holland J. 1975. Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor.Google Scholar
  17. Howard R.A. and Matheson J.E. 1984. Influence diagrams. In: Howard R. and Matheson J. (Eds.), The Principles and Applications of 198 Gòmez and BielzaDecision Analysis, Vol. II, Menlo Park, CA, Strategic Decisions Group, pp. 719-762.Google Scholar
  18. Hsu J.C. 1996. Multiple Comparisons: Theory and Methods. Chapman & Hall, London.Google Scholar
  19. Jensen F.V. 2001. Bayesian Networks and Decision Graphs. Springer, New York.Google Scholar
  20. Jensen F., Jensen F.V., and Dittmer S.L. 1994. From influence diagrams to junction trees. In: Mantaras R.L. and Poole D. (Eds.), Proc. 10th Conf. on Uncertainty in Artificial Intelligence, San Mateo, CA, Morgan Kaufmann, pp. 367-373.Google Scholar
  21. Kirkwood C.W. 1997. Strategic Decision Making. Multiobjective Decision Analysis with Spreadsheets, Duxbury, Belmont, CA.Google Scholar
  22. Kjaerulff U. 1992. Optimal decomposition of probabilistic networks by simulated annealing. Statistics and Computing 2:7-17.CrossRefPubMedGoogle Scholar
  23. Kong A. 1986. Multivariate belief functions and graphical models. Ph.D. Diss., Dept. of Statistics, Harvard University, Cambridge, MA.Google Scholar
  24. Larrañaga P., Kuijpers C.M.H., Poza M., and Murga R.H. 1997. Decomposing Bayesian networks: triangulation of the moral graph with genetic algorithms. Statistics and Computing 7(1):19-34.Google Scholar
  25. Larrañaga P., Kuijpers C.M.H., Murga R.H., Inza I., and Dizdarevic S. 1999. Genetic algorithms for the travelling salesman problem: A review of representations and operators. Artificial Intelligence Review 13:129-170.Google Scholar
  26. Madsen A.L. and Jensen F.V. 1999. Lazy evaluation of symmetric Bayesian decision problems. In: Laskey K.B. and Prade H. (Eds.), Proc. 15th Conf. on Uncertainty in Artificial Intelligence. Morgan Kaufmann, San Francisco, CA, pp. 382-390.Google Scholar
  27. Mahfoud S.W. 1995. Niching methods for genetic algorithms. Ph.D. Diss., University of Illinois, Champaigne, IL.Google Scholar
  28. Mellouli K. 1987. On the propagation of beliefs in networks using the Dempster-Shafer theory of evidence. PhD. Diss., School of Business, University of Kansas, Lawrence, KS.Google Scholar
  29. Michalewicz Z. 1992. Genetic Algorithms + Data Structures = Evolution Programs. Springer, Berlin.Google Scholar
  30. Mitchell M. 1998. An Introduction to Genetic Algorithms. MIT Press, Cambridge, MA.Google Scholar
  31. Nielsen T.D. and Jensen F.V. 1999. Welldefined decision scenarios. In Laskey K.B. and Prade H. (Eds.), Proc. 15th Conf. on Uncertainty in Artificial Intelligence. Morgan Kaufmann, San Francisco, CA, pp. 502-511.Google Scholar
  32. Shachter R.D. 1986. Evaluating influence diagrams. Operations Research 34(6):871-882.Google Scholar
  33. Shachter R.D., Andersen S.K., and Poh K.L. 1990. Directed reduction algorithms and decomposable graphs. In: Bonissone P., Henrion M., Kanal L., and Lemmer J. (Eds.), Proc. 6th Conf. on Uncertainty in Artificial Intelligence. Elsevier, New York, NJ, pp. 237-244.Google Scholar
  34. Shachter R.D., Andersen S.K., and Szolovits P. 1994. Global conditioning for probabilistic inference in belief networks. In: López de Mántaras R. and Poole D. (Eds.), Proc. 10th Conf. on Uncertainty in Artificial Intelligence. Morgan Kaufmann, San Francisco, CA, pp. 514-522.Google Scholar
  35. Shachter R.D. and Ndilikilikesha P. 1993. Using potential influence diagrams for probabilistic inference and decision making. In: Heckerman D. and Mamdani A. (Eds.), Proc. 9th Conf. on Uncertainty in Artificial Intelligence, pp. 383-390.Google Scholar
  36. Shenoy P.P. 1992. Valuation-based systems for Bayesian decision analysis. Operations Research 40(3):463-484.Google Scholar
  37. Shoikhet K. and Geiger D. 1997. A practical algorithm for finding optimal triangulations. In: Proc. 14th Nat. Conf. on Artificial Intelligence. AAAI Press, Menlo Park, CA, pp. 185-190.Google Scholar
  38. Tatman J.A. and Shachter R.D. 1990. Dynamic programming and influence diagrams. IEEE Transactions on Systems, Man and Cybernetics 20(2):365-379.Google Scholar
  39. Venables W. and Ripley B. 1994. Modern Applied Statistics with S-Plus. Springer, New York.Google Scholar
  40. Zhang N.L. 1993. Studies on hypergraphs I: hyperforests. Discrete Applied Mathematics 42:95-112.Google Scholar
  41. Zhang N.L. 1998. Probabilistic inference in influence diagrams. In: Cooper G.F. and Moral S. (Eds.), Proc. 14th Conf. on Uncertainty in Artificial Intelligence. Morgan Kaufmann, San Francisco, CA, pp. 514-522.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • M. Gómez
    • 1
  • C. Bielza
    • 2
  1. 1.Department of Computer Science and Artificial IntelligenceUniversity of GranadaSpain
  2. 2.Department of Artificial IntelligenceTechnical University of MadridSpain

Personalised recommendations