×

Inference using compiled min-based possibilistic causal networks in the presence of interventions. (English) Zbl 1315.68233

Summary: Qualitative possibilistic causal networks are important tools for handling uncertain information in the possibility theory framework. Contrary to possibilistic networks, the compilation principle has not been exploited to ensure causal reasoning in the possibility theory framework. This paper proposes mutilated-based inference approaches and augmented-based inference approaches for qualitative possibilistic causal networks using two compilation methods. The first one is a possibilistic adaptation of the probabilistic inference approach and the second is a purely possibilistic approach based on the transformation of the graphical-based representation into a logic-based one. Each of the proposed methods encodes the network or the possibilistic knowledge base into a propositional base and compiles this output in order to efficiently compute the effect of both observations and interventions. This paper also reports on a set of experimental results showing cases in which augmentation outperforms mutilation under compilation and vice versa.

MSC:

68T37 Reasoning under uncertainty in the context of artificial intelligence
62H86 Multivariate analysis and fuzziness
PDFBibTeX XMLCite
Full Text: DOI

References:

[3] Benferhat, S.; Dubois, D.; Garcia, L.; Prade, H., On the transformation between possibilistic logic bases and possibilistic causal networks, Int. J. Approx. Reason., 29, 135-173 (2002) · Zbl 1015.68204
[5] Benferhat, S.; Smaoui, S., Inferring interventions in product-based possibilistic causal networks, Fuzzy Sets Syst., 169, 26-50 (2011) · Zbl 1214.68395
[8] Cadoli, M.; Donini, F., A survey on knowledge compilation, AI Communications, 3-4, 137-150 (1997)
[11] Darwiche, A., Decomposable negation normal form, J. ACM, 48, 608-647 (2001) · Zbl 1127.03321
[15] Darwiche, A., Modeling and Reasoning with Bayesian Networks (2009), Cambridge University Press: Cambridge University Press New York, NY, USA · Zbl 1231.68003
[16] Darwiche, A.; Marquis, P., A knowledge compilation map, J. Artif. Intell. Res., 17, 229-264 (2002) · Zbl 1045.68131
[17] Dubois, D.; Prade, H., Possibility TheoryAn Approach to Computerized, Processing of Uncertainty (1988), Plenum Press: Plenum Press New York
[18] Dubois, D.; Prade, H., Possibility theory, (Meyers, R. A., Encyclopedia of Complexity and Systems Science (2009), Springer), 6927-6939
[22] Hisdal, E., Conditional possibilities independence and non interaction, Fuzzy Sets Syst., 1 (1978) · Zbl 0393.94050
[23] Pearl, J., Commentgraphical models, causality and intervention, Stat. Sci., 8 (1993)
[24] Pearl, J., CausalityModels, Reasoning and Inference (2000), Cambridge University Press
[25] Shafer, G., Mathematical Theory of Evidence (1976), Princeton University Press · Zbl 0359.62002
[26] Smaoui, S., Réseaux possibilistes hybrides: Représentation des interventions et algorithmes (2007), Université d’Artois
[27] Smets, P., Belief functions, (Smets, P.; Mandani, A.; Dubois, H. P.D., Non Standard Logics for Automated Reasoning (1988), Academic Press: Academic Press London), 253-286
[28] Smets, P.; Kennes, R., The transferable belief model, Artif. Intell., 66, 191-234 (1990) · Zbl 0807.68087
[31] Zadeh, L. A., Fuzzy sets, Inf. Control, 8, 338-353 (1965) · Zbl 0139.24606
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.