Network Fragments: Representing Knowledge for Constructing Probabilistic Models

Abstract

In most current applications of belief networks, domain knowledge is represented by a single belief network that applies to all problem instances in the domain. In more complex domains, problem-specific models must be constructed from a knowledge base encoding probabilistic relationships in the domain. Most work in knowledge-based model construction takes the rule as the basic unit of knowledge. We present a knowledge representation framework that permits the knowledge base designer to specify knowledge in larger semantically meaningful units which we call network fragments. Our framework provides for representation of asymmetric independence and canonical intercausal interaction. We discuss the combination of network fragments to form problem-specific models to reason about particular problem instances. The framework is illustrated using examples from the domain of military situation awareness.

Appears in Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence (UAI1997)

References in corpus (4)

• Context-Specific Independence in Bayesian Networks
• Object-Oriented Bayesian Networks
• Network Engineering for Complex Belief Networks
• A Theoretical Framework for Context-Sensitive Temporal Probability Model Construction with Application to Plan Projection

Cited by in corpus (8)

• Object-Oriented Bayesian Networks
• SPOOK: A System for Probabilistic Object-Oriented Knowledge Representation
• Constructing Situation Specific Belief Networks
• Hypothesis Management in Situation-Specific Network Construction
• Toward General Analysis of Recursive Probability Models
• Representing and Combining Partially Specified CPTs
• An Application of Uncertain Reasoning to Requirements Engineering
• Causal Mechanism-based Model Construction