Possibilistic Graphical Models: From Reasoning to Decision Making

  • Nahla Ben Amor
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8256)


Graphical models are important tools to efficiently represent and analyze uncertain information in knowledge-based systems. The most prominent representatives of these models refer to probability theory. In particular, Bayesian networks [27, 29] have been largely developed and used in real world applications. However, such networks are only appropriate when all numerical data are available, which is not always the case. Indeed, there are some situations such as the case of total ignorance, which are not well handled and which can make the probabilistic reasoning unsound. Therefore non-probabilistic graphical modeling has recently emerged as a promising new area of research. In particular, possibilistic networks [4, 8, 21] appear as noteworthy alternative to probabilistic networks whenever it is necessary to model both uncertainty and imprecision. In fact possibility theory [15] offers a natural and simple model to handle such data and presents an appropriate framework for experts to express their opinions numerically or qualitatively. This leads to two variants of possibilistic networks: product-based networks and min-based networks (also known as qualitative possibilistic networks). The first part of this talk adresses the reasoning problem in possibilistic networks. Several propagation algorithms will be presented with a focus on qualitative networks. The second part concerns the decisional aspect in possibility theory and in particular the sequential decision making in possibilistic decision trees. In fact, the development of possibilistic decision theory has lead to the proposition of a series of possibilistic criteria, namely: optimistic and pessimistic possibilistic qualitative criteria [17], possibilistic likely dominance [14, 20], binary possibilistic utility [23] and possibilistic Choquet integrals [32]. Thus a theoretical study on the complexity of the problem of finding an optimal strategy depending on the monotonicity property of the optimization criteria will be proposed. Details about different parts of this talk can be found in [1-5].


Graphical models Possibility theory Causality Propagation algorithms Decision making Possibilistic decision trees 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ayachi, R., Ben Amor, N., Benferhat, S.: A generic framework for a compilation-based inference in probabilistic and possibilistic networks. To appear in Information Sciences (2013)Google Scholar
  2. 2.
    Ayachi, R., Ben Amor, N., Benferhat, S.: Inference using compiled min-based possibilistic causal networks in the presence of interventions. To appear in Fuzzy Sets and Systems (2013)Google Scholar
  3. 3.
    Ayachi, R., Ben Amor, N., Benferhat, S., Haenni, R.: Compiling possibilistic networks: Alternative approaches to possibilistic inference. In: Uncertainty on Artificial Intelligence (UAI), pp. 40–47 (2010)Google Scholar
  4. 4.
    Ben Amor, N., Benferhat, S., Mellouli, K.: Anytime propagation algorithm for min-based possibilistic graphs. Soft Computing a Fusion of Foundations, Methodologies and Applications 8, 150–161 (2003)Google Scholar
  5. 5.
    Ben Amor, N., Fargier, H., Guezguez, W.: Possibilistic sequential decision making. In: Technical report LARODEC/2013. Laboratoire de Recherche Opérationnelle, de Décision et de Contrôle de processus (LARODEC), Institut Supérieur de Gestion Tunis (2013)Google Scholar
  6. 6.
    Benferhat, S., Dubois, D., Garcia, L., Prade, H.: On the transformation between possibilistic logic bases and possibilistic causal networks. International Journal on Approximate Reasoning 29 (2002)Google Scholar
  7. 7.
    Benferhat, S., Smaoui, S.: Possibilistic causal networks for handling interventions: A new propagation algorithm. In: American Association for Artificial Intelligence Conference (AAAI), pp. 373–378 (2007)Google Scholar
  8. 8.
    Borgelt, C., Gebhardt, J., Kruse, R.: Possibilistic graphical models. In: International School for the Synthesis of Expert Knowledge (ISSEK), Udine, Italy (1998)Google Scholar
  9. 9.
    Borgelt, C., Steinbrecher, M., Kruse, R.R.: Graphical models: representations for learning, reasoning and data mining, vol. 704. Wiley (2009)Google Scholar
  10. 10.
    Cadoli, M., Donini, F.M.: A survey on knowledge compilation. AI Communications–The European Journal for Artificial Intelligence (10), 137–150 (1998)Google Scholar
  11. 11.
    Choquet, G.: Théorie des capacités. Technical report, Annales de l’institut Fourier, Grenoble (1953)Google Scholar
  12. 12.
    Cooper, G.F.: Computational complexity of probabilistic inference using bayesian belief networks. Artificial Intelligence 42, 393–405 (1990)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Darwiche, A.: A logical approach to factoring belief networks. In: Knowledge Representation, pp. 409–420. ACM (2002)Google Scholar
  14. 14.
    Dubois, D., Fargier, H., Perny, P.: Qualitative decision theory with preference relations and comparative uncertainty: An axiomatic approach. Artificial Intelligence 148(1-2), 219–260 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Dubois, D., Prade, H.: Possibility theory: An approach to computerized, Processing of uncertainty. Plenum Press, New York (1988)CrossRefzbMATHGoogle Scholar
  16. 16.
    Dubois, D., Prade, H.: Epistemic entrenchment and possibilistic logic. Artificial Intelligence 50, 223–239 (1991)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Dubois, D., Prade, H.: Possibility theory as a basis for qualitative decision theory. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1924–1930 (1995)Google Scholar
  18. 18.
    Garcia, L., Sabbadin, R.: Possibilistic influence diagrams. In: Brewka, G., et al. (eds.) ECAI, Italie, Riva del Garda, pp. 372–376 (2006)Google Scholar
  19. 19.
    Fargier, H., Ben Amor, N., Guezguez, W.: On the complexity of decision making in possibilistic decision trees. In: Uncertainty in Artificial Intelligence (UAI 2011), pp. 203–210 (2011)Google Scholar
  20. 20.
    Fargier, H., Perny, P.: Qualitative models for decision under uncertainty without the commensurability assumption. In: Uncertainty in Artificial Intelligence (UAI), pp. 188–195 (1999)Google Scholar
  21. 21.
    Fonck, P.: Propagating uncertainty in a directed acyclic graph. In: International Conference on Information Processing of Uncertainty in Knowledge Based Systems (IPMU), Palma de Mallorca, pp. 17–20 (1992)Google Scholar
  22. 22.
    Giang, P.H., Shenoy, P.P.: A qualitative linear utility theory for spohn’s theory of epistemic beliefs. In: Uncertainty in Artificial Intelligence (UAI), pp. 220–229 (2000)Google Scholar
  23. 23.
    Giang, P.H., Shenoy, P.P.: A comparison of axiomatic approaches to qualitative decision making using possibility theory. In: Uncertainty in Artificial Intelligence (UAI), pp. 162–170 (2001)Google Scholar
  24. 24.
    Giang, P.H., Shenoy, P.P.: Two axiomatic approaches to decision making using possibility theory. European Journal of Operational Research 162(2), 450–467 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Hisdal, E.: Conditional possibilities independence and non interaction. Fuzzy Sets and Systems 1, 283–297 (1978)CrossRefzbMATHGoogle Scholar
  26. 26.
    Howard, R.A., Matheson, J.E.: Influence diagrams. The Principles and Applications of Decision Analysis 2, 720–761 (1984)Google Scholar
  27. 27.
    Jensen, F.V.: Introduction to Bayesien networks. UCL Press, University College, London (1996)Google Scholar
  28. 28.
    Mark, C., Darwiche, A.: Compiling bayesian networks with local structure. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1306–1312 (2005)Google Scholar
  29. 29.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)Google Scholar
  30. 30.
    Pearl, J.: Causality: Models, reasoning and inference. MIT Press (2000)Google Scholar
  31. 31.
    Raiffa, H.: Decision analysis. Addison-Welsley Publishing Company, Toronto (1968)zbMATHGoogle Scholar
  32. 32.
    Rebille, Y.: Decision making over necessity measures through the choquet integral criterion. Fuzzy Sets and Systems 157(23), 3025–3039 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  33. 33.
    Spohn, W.: A general non-probabilistic theory of inductive reasoning. In: Uncertainty in Artificial Intelligence (UAI), pp. 315–322. Elsevier Science (1990)Google Scholar
  34. 34.
    von Neumann, J., Morgenstern, O.: Theory of games and economic behavior. Princeton University Press (1948)Google Scholar
  35. 35.
    Zadeh, L.A.: Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets and Systems 1, 3–28 (1978)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Nahla Ben Amor
    • 1
  1. 1.Laboratoire de Recherche Opérationnelle, de Décision et de Contrôle de processus (LARODEC), Institut Supérieur de Gestion TunisUniversité de TunisTunisia

Personalised recommendations