Conflict-driven ASP Solving with External Sources

TL;DR

This paper introduces a new conflict-driven algorithm for HEX-programs in Answer Set Programming that incorporates learning from external sources, significantly improving scalability and performance over existing translation-based methods.

Contribution

It presents a novel native evaluation algorithm for HEX-programs that extends conflict-driven ASP solving with learning techniques to efficiently handle external sources.

Findings

Learning reduces runtime and candidate sets.

Algorithm scales better with external source accesses.

External source evaluations improve solving efficiency.

Abstract

Answer Set Programming (ASP) is a well-known problem solving approach based on nonmonotonic logic programs and efficient solvers. To enable access to external information, HEX-programs extend programs with external atoms, which allow for a bidirectional communication between the logic program and external sources of computation (e.g., description logic reasoners and Web resources). Current solvers evaluate HEX-programs by a translation to ASP itself, in which values of external atoms are guessed and verified after the ordinary answer set computation. This elegant approach does not scale with the number of external accesses in general, in particular in presence of nondeterminism (which is instrumental for ASP). In this paper, we present a novel, native algorithm for evaluating HEX-programs which uses learning techniques. In particular, we extend conflict-driven ASP solving techniques, which prevent the solver from running into the same conflict again, from ordinary to HEX-programs. We show how to gain additional knowledge from external source evaluations and how to use it in a conflict-driven algorithm. We first target the uninformed case, i.e., when we have no extra information on external sources, and then extend our approach to the case where additional meta-information is available. Experiments show that learning from external sources can significantly decrease both the runtime and the number of considered candidate compatible sets.