{"type":"ScholarlyArticle","title":"Abductive Learning with Ground Knowledge Base","authors":[{"name":"Le-Wen Cai","slug":"le-wen-cai","given":"Le-Wen","family":"Cai","affiliation":""},{"name":"Wang-Zhou Dai","slug":"wang-zhou-dai","given":"Wang-Zhou","family":"Dai","affiliation":""},{"name":"Yu-Xuan Huang","slug":"yu-xuan-huang","given":"Yu-Xuan","family":"Huang","affiliation":""},{"name":"Yu-Feng Li","slug":"yu-feng-li","given":"Yu-Feng","family":"Li","affiliation":""},{"name":"Stephen Muggleton","slug":"stephen-muggleton","given":"Stephen","family":"Muggleton","affiliation":""},{"name":"Yuan Jiang","slug":"yuan-jiang","given":"Yuan","family":"Jiang","affiliation":""}],"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.","doi":"10.24963/ijcai.2021/250","url":"https://ijcai.org/proceedings/2021/250","pdf":"https://ijcai.org/proceedings/2021/0250.pdf","markdown":"https://ijcai.org/proceedings/2021/250.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/250","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":250,"pages":{"first":1815,"last":1821},"keywords":["Machine Learning: Weakly Supervised Learning","Machine Learning: Knowledge Aided Learning","Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}