Learning extensible multi-entity directed graphical models

Graphical models have become a standard tool for representing complex probability models in statistics and artificial intelligence. In problems arising in artificial intelligence, it is useful to use the belief network formalism to represent uncertain relationships among variables in the domain, but it may not be possible to use a single, fixed belief network to encompass all problem instances. This is because the number of entities to be reasoned about and their relationships to each other varies from problem instance to problem instance. This paper describes a framework for representing probabilistic knowledge as fragments of belief networks and an approach to learning both structure and parameters from observations.