Learning Ground CP-logic Theories by means of Bayesian Network Techniques

Abstract. Causal relationships are present in many application domains. CP-logic is a probabilistic modeling language that is especially designed to express such relationships. This paper investigates the learning of CP-theories from examples, and focusses on structure learning. The proposed approach is based on a transformation between CP-logic theories and Bayesian networks, that is, the method applies Bayesian network learning techniques to learn a CP-theory in the form of an equivalent Bayesian network. We propose a constrained refinement operator for such networks that guarantees equivalence to a valid CP-theory. We experimentally compare our method to a standard method for learning Bayesian networks. This shows that CP-theories can be learned more efficiently than Bayesian networks given that causal relationships are present in the domain.