AILGMLApr 21, 2020

Knowledge Refactoring for Inductive Program Synthesis

arXiv:2004.09931v38 citations
AI Analysis

This addresses the problem of inefficient learning for AI systems by enabling more compact and less redundant knowledge bases, though it is incremental as it builds on existing inductive logic programming methods.

The paper tackled the problem of inefficient knowledge representation in machine learning by introducing knowledge refactoring to reduce size and redundancy, focusing on inductive logic programming. The result showed that learning from refactored knowledge improved predictive accuracies fourfold and reduced learning times by half in domains like string transformations and Lego structures.

Humans constantly restructure knowledge to use it more efficiently. Our goal is to give a machine learning system similar abilities so that it can learn more efficiently. We introduce the \textit{knowledge refactoring} problem, where the goal is to restructure a learner's knowledge base to reduce its size and to minimise redundancy in it. We focus on inductive logic programming, where the knowledge base is a logic program. We introduce Knorf, a system which solves the refactoring problem using constraint optimisation. We evaluate our approach on two program induction domains: real-world string transformations and building Lego structures. Our experiments show that learning from refactored knowledge can improve predictive accuracies fourfold and reduce learning times by half.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes