On the complexity of inference about probabilistic relational models

Abstract We investigate the complexity of probabilistic inference from knowledge bases that encode probability distributions on finite domain relational structures. Our interest here lies in the complexity in terms of the domain under consideration in a specific application instance. We obtain the result that assuming NETIME ≠ ETIME this problem is not polynomial for reasonably expressive representation systems. The main consequence of this result is that it is unlikely to find inference techniques with a better worst-case behavior than the commonly employed strategy of constructing standard Bayesian networks over ground atoms (knowledge based model construction).

[1]  Peter Haddawy,et al.  Answering Queries from Context-Sensitive Probabilistic Knowledge Bases , 1997, Theor. Comput. Sci..

[2]  Peter Haddawy,et al.  Anytime Deduction for Probabilistic Logic , 1994, Artif. Intell..

[3]  David S. Johnson,et al.  A Catalog of Complexity Classes , 1991, Handbook of Theoretical Computer Science, Volume A: Algorithms and Complexity.

[4]  Peter Haddawy,et al.  Generating Bayesian Networks from Probablity Logic Knowledge Bases , 1994, UAI.

[5]  Manfred Jaeger,et al.  Convergence results for relational Bayesian networks , 1998, Proceedings. Thirteenth Annual IEEE Symposium on Logic in Computer Science (Cat. No.98CB36226).

[6]  Ker-I Ko,et al.  Studies in complexity theory , 1986 .

[7]  Max Henrion,et al.  Propagating uncertainty in bayesian networks by probabilistic logic sampling , 1986, UAI.

[8]  Manfred Jaeger,et al.  Relational Bayesian Networks , 1997, UAI.

[9]  Robert P. Goldman,et al.  From knowledge bases to decision models , 1992, The Knowledge Engineering Review.

[10]  David Poole,et al.  Probabilistic Horn Abduction and Bayesian Networks , 1993, Artif. Intell..

[11]  Nils J. Nilsson,et al.  Probabilistic Logic * , 2022 .

[12]  J. Van Leeuwen,et al.  Handbook of theoretical computer science - Part A: Algorithms and complexity; Part B: Formal models and semantics , 1990 .

[13]  John S. Breese,et al.  CONSTRUCTION OF BELIEF AND DECISION NETWORKS , 1992, Comput. Intell..

[14]  Lise Getoor,et al.  Learning Probabilistic Relational Models , 1999, IJCAI.

[15]  Gregory F. Cooper,et al.  The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks , 1990, Artif. Intell..

[16]  Fahiem Bacchus,et al.  Representing and reasoning with probabilistic knowledge , 1988 .

[17]  Laks V. S. Lakshmanan,et al.  Probabilistic Deductive Databases , 1994, ILPS.

[18]  Avi Pfeffer,et al.  Probabilistic Frame-Based Systems , 1998, AAAI/IAAI.

[19]  Michael Luby,et al.  Approximating Probabilistic Inference in Bayesian Belief Networks is NP-Hard , 1993, Artif. Intell..

[20]  A. Saffiotti,et al.  Inference-Driven Construction of Valuation Systems from First-Order Clauses , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[21]  V. S. Subrahmanian,et al.  Probabilistic Logic Programming , 1992, Inf. Comput..

[22]  Neil D. Jones,et al.  Turing machines and the spectra of first-order formulas with equality , 1972, STOC.