Imparo is complete by inverse subsumption

TL;DR

This paper proves that the ILP system Imparo is complete when using inverse subsumption, ensuring it can learn correct hypotheses based on background knowledge and examples.

Contribution

It establishes the completeness of Imparo with inverse subsumption, a novel approach compared to inverse entailment in ILP.

Findings

Imparo is complete by inverse subsumption for definite hypotheses

Existence of a connected theory T for background B and examples E

H subsumes T in the learning process

Abstract

In Inverse subsumption for complete explanatory induction Yamamoto et al. investigate which inductive logic programming systems can learn a correct hypothesis $H$ by using the inverse subsumption instead of inverse entailment. We prove that inductive logic programming system Imparo is complete by inverse subsumption for learning a correct definite hypothesis $H$ wrt the definite background theory $B$ and ground atomic examples $E$, by establishing that there exists a connected theory $T$ for $B$ and $E$ such that $H$ subsumes $T$.