Proceedings

Abductive Learning with Ground Knowledge Base

Le-Wen Cai, Wang-Zhou Dai, Yu-Xuan Huang, Yu-Feng Li, Stephen Muggleton, Yuan Jiang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1815-1821.

https://doi.org/10.24963/ijcai.2021/250

Keywords

  • Machine Learning: Weakly Supervised Learning
  • Machine Learning: Knowledge Aided Learning
  • Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Abstract

Abductive Learning is a framework that combines machine learning with first-order logical reasoning. It allows machine learning models to exploit complex symbolic domain knowledge represented by first-order logic rules. However, it is challenging to obtain or express the ground-truth domain knowledge explicitly as first-order logic rules in many applications. The only accessible knowledge base is implicitly represented by groundings, i.e., propositions or atomic formulas without variables. This paper proposes Grounded Abductive Learning (GABL) to enhance machine learning models with abductive reasoning in a ground domain knowledge base, which offers inexact supervision through a set of logic propositions. We apply GABL on two weakly supervised learning problems and found that the model's initial accuracy plays a crucial role in learning. The results on a real-world OCR task show that GABL can significantly reduce the effort of data labeling than the compared methods.

Le-Wen Cai, Wang-Zhou Dai, Yu-Xuan Huang, Yu-Feng Li, Stephen Muggleton, and Yuan Jiang. 2021. Abductive Learning with Ground Knowledge Base. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1815–1821. https://doi.org/10.24963/ijcai.2021/250
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards