Abductive Knowledge Induction From Raw Data

TL;DR

This paper introduces Meta_Abd, a novel neuro-symbolic system that jointly learns neural networks and induces recursive logic theories from raw data, addressing the knowledge source problem in reasoning tasks.

Contribution

Meta_Abd uniquely combines abduction and induction to learn neural networks and logic theories simultaneously from raw data, including predicate invention and recursive logic induction.

Findings

Outperforms existing systems in accuracy and data efficiency

Induces reusable logic programs as background knowledge

First system to jointly learn neural networks and recursive logic theories from scratch

Abstract

For many reasoning-heavy tasks involving raw inputs, it is challenging to design an appropriate end-to-end learning pipeline. Neuro-Symbolic Learning, divide the process into sub-symbolic perception and symbolic reasoning, trying to utilise data-driven machine learning and knowledge-driven reasoning simultaneously. However, they suffer from the exponential computational complexity within the interface between these two components, where the sub-symbolic learning model lacks direct supervision, and the symbolic model lacks accurate input facts. Hence, most of them assume the existence of a strong symbolic knowledge base and only learn the perception model while avoiding a crucial problem: where does the knowledge come from? In this paper, we present Abductive Meta-Interpretive Learning ($Meta_{Abd}$) that unites abduction and induction to learn neural networks and induce logic theories jointly from raw data. Experimental results demonstrate that $Meta_{Abd}$ not only outperforms the compared systems in predictive accuracy and data efficiency but also induces logic programs that can be re-used as background knowledge in subsequent learning tasks. To the best of our knowledge, $Meta_{Abd}$ is the first system that can jointly learn neural networks from scratch and induce recursive first-order logic theories with predicate invention.