Most Relevant Explanation in Bayesian Networks

Journal of Artificial Intelligence Research

A major inference task in Bayesian networks is explaining why some variables are observed in their particular states using a set of target variables. Existing methods for solving this problem often generate explanations that are either too simple (underspecified) or too complex (overspecified). In this paper, we introduce a method called Most Relevant Explanation (MRE) which finds a partial instantiation of the target variables that maximizes the generalized Bayes factor (GBF) as the best explanation for the given evidence. Our study shows that GBF has several theoretical properties that enable MRE to automatically identify the most relevant target variables in forming its explanation. In particular, conditional Bayes factor (CBF), defined as the GBF of a new explanation conditioned on an existing explanation, provides a soft measure on the degree of relevance of the variables in the new explanation in explaining the evidence given the existing explanation. As a result, MRE is able to automatically prune less relevant variables from its explanation. We also show that CBF is able to capture well the explaining-away phenomenon that is often represented in Bayesian networks. Moreover, we define two dominance relations between the candidate solutions and use the relations to generalize MRE to find a set of top explanations that is both diverse and representative. Case studies on several benchmark diagnostic Bayesian networks show that MRE is often able to find explanatory hypotheses that are not only precise but also concise.


Explaining Predictions in Bayesian Networks and Influence Diagrams

AAAI Conferences

As Bayesian Networks and Influence Diagrams are being used more and more widely, the importance of an efficient explanation mechanism becomes more apparent. We focus on predictive explanations, the ones designed to explain predictions and recommendations of probabilistic systems. We analyze the issues involved in defining, computing and evaluating such explanations and present an algorithm to compute them. Introduction As knowledge-based reasoning systems begin addressing real-world problems, they are often designed to be used not by experts but by people unfamiliar with the domain. Such people are unlikely to accept system's prediction or advice without some explanation. In addition, the systems' ever increasing size makes their computations more and more difficult to follow even for their creators. This situation makes an explanation mechanism critical for making these systems useful and widely accepted. Probabilistic systems, such as Bayesian Networks (Pearl 1988) and Influence Diagrams (Howard and Matheson 1984), need such a mechanism even more than others. Human judgment under uncertainty differs considerably from the idealized rationality of probability and decision theories.


Most Relevant Explanation in Bayesian Networks

Journal of Artificial Intelligence Research

A major inference task in Bayesian networks is explaining why some variables are observed in their particular states using a set of target variables. Existing methods for solving this problem often generate explanations that are either too simple (underspecified) or too complex (overspecified). In this paper, we introduce a method called Most Relevant Explanation (MRE) which finds a partial instantiation of the target variables that maximizes the generalized Bayes factor (GBF) as the best explanation for the given evidence. Our study shows that GBF has several theoretical properties that enable MRE to automatically identify the most relevant target variables in forming its explanation. In particular, conditional Bayes factor (CBF), defined as the GBF of a new explanation conditioned on an existing explanation, provides a soft measure on the degree of relevance of the variables in the new explanation in explaining the evidence given the existing explanation. As a result, MRE is able to automatically prune less relevant variables from its explanation. We also show that CBF is able to capture well the explaining-away phenomenon that is often represented in Bayesian networks. Moreover, we define two dominance relations between the candidate solutions and use the relations to generalize MRE to find a set of top explanations that is both diverse and representative. Case studies on several benchmark diagnostic Bayesian networks show that MRE is often able to find explanatory hypotheses that are not only precise but also concise.


Shchekotykhin

AAAI Conferences

Broad application of answer set programming (ASP) for declarative problem solving requires the development of tools supporting the coding process. Program debugging is one of the crucial activities within this process. Modern ASP debugging approaches allow efficient computation of possible explanations of a fault. However, even for a small program a debugger might return a large number of possible explanations and selection of the correct one must be done manually. In this paper we present an interactive query-based ASP debugging method which extends previous approaches and finds the preferred explanation by means of observations. The system automatically generates a sequence of queries to a programmer asking whether a set of ground atoms must be true in all (cautiously) or some (bravely) answer sets of the program. Since some queries can be more informative than the others, we discuss query selection strategies which - given user's preferences for an explanation - can find the most informative query reducing the overall number of queries required for the identification of a preferred explanation.


An Explanation Mechanism for Bayesian Inferencing Systems

arXiv.org Artificial Intelligence

Explanation facilities are a particularly important feature of expert system frameworks. It is an area in which traditional rule-based expert system frameworks have had mixed results. While explanations about control are well handled, facilities are needed for generating better explanations concerning knowledge base content. This paper approaches the explanation problem by examining the effect an event has on a variable of interest within a symmetric Bayesian inferencing system. We argue that any effect measure operating in this context must satisfy certain properties. Such a measure is proposed. It forms the basis for an explanation facility which allows the user of the Generalized Bayesian Inferencing System to question the meaning of the knowledge base. That facility is described in detail.