Learning Abductive Logic Programs

We propose an approach for the integration of abduction and induction in Logic Programming. In particular, we show how it is possible to learn, by induction, an abductive logic program. Abducibles and integrity constraints can be specified by the user as content of the background knowledge or can be generated by the abductive/inductive process. We ground our framework on the generalized stable model semantics defined for abductive logic programs, and its associated proof procedure. By integrating Inductive Logic Programming with Abductive Logic Programming we can learn in presence of incomplete knowledge, take into account negative examples and generate exceptions to (possibly induced) rules