The goal of inductive logic programming (ILP) is to learn a program that explains a set of examples.Until recently, most research on ILP targeted learning Prolog programs. The ILASP systeminstead learns answer set programs (ASP). Learning such expressive programs widens the applicabilityof ILP considerably; for example, enabling preference learning, learning common-senseknowledge, including defaults and exceptions, and learning non-deterministic theories. Earlyversions of ILASP can be considered meta-level ILP approaches, which encode a learning taskas a logic program and delegate the search to an ASP solver. More recently, ILASP has shiftedtowards a new method, inspired by conflict-driven SAT and ASP solvers. The fundamental ideaof the approach, called Conflict-driven ILP (CDILP), is to iteratively interleave the search fora hypothesis with the generation of constraints which explain why the current hypothesis doesnot cover a particular example. These coverage constraints allow ILASP to rule out not just thecurrent hypothesis, but an entire class of hypotheses that do not satisfy the coverage constraint.This article formalises the CDILP approach and presents the ILASP3 and ILASP4 systems forCDILP, which are demonstrated to be more scalable than previous ILASP systems, particularlyin the presence of noise.
展开▼
