Graphical Representations of Consensus Belief

Graphical models based on conditional independence support concise encodings of the subjective belief of a single agent. A natural question is whether the consensus belief of a group of agents can be represented with equal parsimony. We prove, under relatively mild assumptions, that even if everyone agrees on a common graph topology, no method of combining beliefs can maintain that structure. Even weaker conditions rule out local aggregation within conditional probability tables. On a more positive note, we show that if probabilities are combined with the logarithmic opinion pool (LogOP), then commonly held Markov independencies are maintained. This suggests a straightforward procedure for constructing a consensus Markov network. We describe an algorithm for computing the LogOP with time complexity comparable to that of exact Bayesian inference.

[1]  L. Tippett,et al.  Applied Statistics. A Journal of the Royal Statistical Society , 1952 .

[2]  A. Madansky.  EXTERNALLY BAYESIAN GROUPS , 1964 .

[3]  M. Schervish,et al.  Characterization of Externally Bayesian Pooling Operators , 1986 .

[4]  T. Speed,et al.  Markov Fields and Log-Linear Interaction Models for Contingency Tables , 1980 .

[5]  Bruce Abramson,et al.  The Topological Fusion of Bayes Nets , 1992, UAI.

[6]  L. Goddard,et al.  Operations Research (OR) , 2007 .

[7]  Ross D. Shachter.  Probabilistic Inference and Influence Diagrams , 1988, Oper. Res..

[8]  Bruce Abramson,et al.  Some Complexity Considerations in the Combination of Belief Networks , 1993, UAI.

[9]  Chiuh-Cheng Chyu.  Decomposable Probabilistic Influence Diagrams , 1989 .

[10]  Carl G. Wagner.  Aggregating subjective probabilities: some limitative theorems , 1984, Notre Dame J. Formal Log..

[11]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[12]  C. Genest.  A Characterization Theorem for Externally Bayesian Groups , 1984 .

[13]  G. Yule.  NOTES ON THE THEORY OF ASSOCIATION OF ATTRIBUTES IN STATISTICS , 1903 .

[14]  C. Genest.  A Conflict between Two Axioms for Combining Subjective Distributions , 1984 .

[15]  C. Genest.  Pooling operators with the marginalization property , 1984 .

[16]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[17]  Ross D. Shachter,et al.  Directed reduction algorithms and decomposable graphs , 1990, UAI.

[18]  R. Lathe.  Phd by thesis , 1988, Nature.

[19]  Richard E. Neapolitan,et al.  Probabilistic reasoning in expert systems - theory and algorithms , 2012 .

[20]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[21]  Robert A. Jacobs,et al.  Methods For Combining Experts' Probability Assessments , 1995, Neural Computation.

[22]  Norman C. Dalkey,et al.  Toward a theory of group estimation , 1975 .

[23]  Alice M. Obenchain-Leeson,et al.  Volume 6 , 1998 .

[24]  J. N. R. Jeffers,et al.  Graphical Models in Applied Multivariate Statistics. , 1990 .

[25]  Ton Kloks.  Treewidth, Computations and Approximations , 1994, Lecture Notes in Computer Science.

[26]  M. Degroot,et al.  Bayesian Statistics 2. , 1987 .

[27]  Christian Genest,et al.  Combining Probability Distributions: A Critique and an Annotated Bibliography , 1986 .

[28]  Yang Xiang,et al.  A Probabilistic Framework for Cooperative Multi-Agent Distributed Interpretation and Optimization of Communication , 1996, Artif. Intell..

[29]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

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

[31]  C. Genest,et al.  Further evidence against independence preservation in expert judgement synthesis , 1987 .