Parallel Constraint-Driven Inductive Logic Programming

TL;DR

This paper introduces parallel techniques for constraint-driven inductive logic programming to improve scalability on multi-core systems, demonstrating significant reductions in learning times and emphasizing the importance of worker communication.

Contribution

It presents a novel parallelization approach for ILP based on constraint accumulation, enhancing scalability and efficiency in multi-core environments.

Findings

Parallelization reduces learning times significantly.

Sharing constraints among workers improves performance.

Effective communication is crucial for scalability.

Abstract

Multi-core machines are ubiquitous. However, most inductive logic programming (ILP) approaches use only a single core, which severely limits their scalability. To address this limitation, we introduce parallel techniques based on constraint-driven ILP where the goal is to accumulate constraints to restrict the hypothesis space. Our experiments on two domains (program synthesis and inductive general game playing) show that (i) parallelisation can substantially reduce learning times, and (ii) worker communication (i.e. sharing constraints) is important for good performance.