Inductive logic programming at 30: a new introduction

TL;DR

This paper provides a comprehensive, updated introduction to inductive logic programming (ILP), covering its foundations, systems, applications, and future research directions at its 30-year milestone.

Contribution

It offers a new, detailed overview of ILP, including logical notation, system comparisons, and insights into current challenges and future research avenues.

Findings

Comparison of ILP systems on multiple dimensions

Description of four key ILP systems (Aleph, TILDE, ASPAL, Metagol)

Identification of current limitations and future research directions

Abstract

Inductive logic programming (ILP) is a form of machine learning. The goal of ILP is to induce a hypothesis (a set of logical rules) that generalises training examples. As ILP turns 30, we provide a new introduction to the field. We introduce the necessary logical notation and the main learning settings; describe the building blocks of an ILP system; compare several systems on several dimensions; describe four systems (Aleph, TILDE, ASPAL, and Metagol); highlight key application areas; and, finally, summarise current limitations and directions for future research.