On probabilistic inference by weighted model counting

Abstract

A recent and effective approach to probabilistic inference calls for reducing the problem to one of weighted model counting (WMC) on a propositional knowledge base. Specifically, the approach calls for encoding the probabilistic model, typically a Bayesian network, as a propositional knowledge base in conjunctive normal form (CNF) with weights associated to each model according to the network parameters. Given this CNF, computing the probability of some evidence becomes a matter of summing the weights of all CNF models consistent with the evidence. A number of variations on this approach have appeared in the literature recently, that vary across three orthogonal dimensions. The first dimension concerns the specific encoding used to convert a Bayesian network into a CNF. The second dimensions relates to whether weighted model counting is performed using a search algorithm on the CNF, or by compiling the CNF into a structure that renders WMC a polytime operation in the size of the compiled structure. The third dimension deals with the specific properties of network parameters (local structure) which are captured in the CNF encoding. In this paper, we discuss recent work in this area across the above three dimensions, and demonstrate empirically its practical importance in significantly expanding the reach of exact probabilistic inference. We restrict our discussion to exact inference and model counting, even though other proposals have been extended for approximate inference and approximate model counting.

Improved Algorithms for Data Visualization in Forensic DNA Analysis

“…Concept of probabilistic inference algorithms can be easily understood using the method proposed known as singly connected Bayesian networks (SCBNs) that is a special case of BNs. Concept of probabilistic inference is being used in relation with Bayesian networks by [19].…”

“…Researchers [19] define the semantics of Bayesian networks in a form of joint distribution. A novel method where it is constructed from the probability distributions of DNA sequence.…”

“…The directed acyclic graph is a BN relative to a set of variables if the joint probability distribution of the node variables can be written as the product of the local distributions of each node and its parents. Bayesian networks approach like this is employed by [19] to a set of variables of each node as: …”

Lifted generative learning of Markov logic networks

“…These are regularities that arise from using Boolean logic to compactly define potentials (Chavira and Darwiche 2008). They are not exploited by factor-based lifted inference algorithms, such as FOVE (de Salvo Braz et al 2005).…”

Cutset Networks: A Simple, Tractable, and Scalable Approach for Improving the Accuracy of Chow-Liu Trees

“…If the cutset is bounded, then cutset conditioning is tractable. However, note that unlike classic cutset conditioning, cutset networks can take advantage of determinism [3,12] and context-specific independence [2] by allowing different variables to be conditioned on at the same level in the OR search tree. As a result, they can yield a compact representation even if the size of the cutset is arbitrarily large.…”