Connrmation-guided Discovery of Rst-order Rules with Tertius

This paper deals with learning rst-order logic rules from data lacking an explicit classi cation predicate. Consequently, the learned rules are not restricted to predicate de nitions as in supervised inductive logic programming. First-order logic o ers the ability to deal with structured, multi-relational knowledge. Possible applications include rst-order knowledge discovery, induction of integrity constraints in databases, multiple predicate learning, and learning mixed theories of predicate de nitions and integrity constraints. One of the contributions of our work is a heuristic measure of con rmation, trading o novelty and satisfaction of the rule. The approach has been implemented in the Tertius system. The system performs an optimal bestrst search, nding the k most con rmed hypotheses, and includes a non-redundant re nement operator to avoid duplicates in the search. Tertius can be adapted to many di erent domains by tuning its parameters, and it can deal either with individual-based representations by upgrading propositional representations to rst-order, or with general logical rules. We describe a number of experiments demonstrating the feasibility and exibility of our approach.