Understanding and improving ontology reasoning efficiency through learning and ranking

Yong-Bin Kang, Shonali Krishnaswamy, Wudhichart Sawangphol, Lianli Gao, Yuan-Fang Li

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Ontologies are the fundamental building blocks of the Semantic Web and Linked Data. Reasoning is critical to ensure the logical consistency of ontologies, and to compute inferred knowledge from an ontology. It has been shown both theoretically and empirically that, despite decades of intensive work on optimising ontology reasoning algorithms, performing core reasoning tasks on large and expressive ontologies is time-consuming and resource-intensive. In this paper, we present the meta-reasoning framework R2O2* to tackle the important problems of understanding the source of TBox reasoning hardness and predicting and optimising TBox reasoning efficiency by exploiting machine learning techniques. R2O2* combines state-of-the-art OWL 2 DL reasoners as well as an efficient OWL 2 EL reasoner as components, and predicts the most efficient one by using an ensemble of robust learning algorithms including XGBoost and Random Forests. A comprehensive evaluation on a large and carefully curated ontology corpus shows that R2O2* outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.

Original languageEnglish
Article number101412
Number of pages17
JournalInformation Systems
Volume87
DOIs
Publication statusPublished - 1 Jan 2020

Keywords

  • Learning
  • Meta-reasoning
  • Metrics
  • Ontology
  • OWL
  • Performance prediction
  • Reasoning
  • Semantic web

Cite this

Kang, Yong-Bin ; Krishnaswamy, Shonali ; Sawangphol, Wudhichart ; Gao, Lianli ; Li, Yuan-Fang. / Understanding and improving ontology reasoning efficiency through learning and ranking. In: Information Systems. 2020 ; Vol. 87.
@article{cec7f56873824a2691e7d5ea81220a7e,
title = "Understanding and improving ontology reasoning efficiency through learning and ranking",
abstract = "Ontologies are the fundamental building blocks of the Semantic Web and Linked Data. Reasoning is critical to ensure the logical consistency of ontologies, and to compute inferred knowledge from an ontology. It has been shown both theoretically and empirically that, despite decades of intensive work on optimising ontology reasoning algorithms, performing core reasoning tasks on large and expressive ontologies is time-consuming and resource-intensive. In this paper, we present the meta-reasoning framework R2O2* to tackle the important problems of understanding the source of TBox reasoning hardness and predicting and optimising TBox reasoning efficiency by exploiting machine learning techniques. R2O2* combines state-of-the-art OWL 2 DL reasoners as well as an efficient OWL 2 EL reasoner as components, and predicts the most efficient one by using an ensemble of robust learning algorithms including XGBoost and Random Forests. A comprehensive evaluation on a large and carefully curated ontology corpus shows that R2O2* outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.",
keywords = "Learning, Meta-reasoning, Metrics, Ontology, OWL, Performance prediction, Reasoning, Semantic web",
author = "Yong-Bin Kang and Shonali Krishnaswamy and Wudhichart Sawangphol and Lianli Gao and Yuan-Fang Li",
year = "2020",
month = "1",
day = "1",
doi = "10.1016/j.is.2019.07.002",
language = "English",
volume = "87",
journal = "Information Systems",
issn = "0306-4379",
publisher = "Elsevier",

}

Understanding and improving ontology reasoning efficiency through learning and ranking. / Kang, Yong-Bin; Krishnaswamy, Shonali; Sawangphol, Wudhichart; Gao, Lianli; Li, Yuan-Fang.

In: Information Systems, Vol. 87, 101412, 01.01.2020.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Understanding and improving ontology reasoning efficiency through learning and ranking

AU - Kang, Yong-Bin

AU - Krishnaswamy, Shonali

AU - Sawangphol, Wudhichart

AU - Gao, Lianli

AU - Li, Yuan-Fang

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Ontologies are the fundamental building blocks of the Semantic Web and Linked Data. Reasoning is critical to ensure the logical consistency of ontologies, and to compute inferred knowledge from an ontology. It has been shown both theoretically and empirically that, despite decades of intensive work on optimising ontology reasoning algorithms, performing core reasoning tasks on large and expressive ontologies is time-consuming and resource-intensive. In this paper, we present the meta-reasoning framework R2O2* to tackle the important problems of understanding the source of TBox reasoning hardness and predicting and optimising TBox reasoning efficiency by exploiting machine learning techniques. R2O2* combines state-of-the-art OWL 2 DL reasoners as well as an efficient OWL 2 EL reasoner as components, and predicts the most efficient one by using an ensemble of robust learning algorithms including XGBoost and Random Forests. A comprehensive evaluation on a large and carefully curated ontology corpus shows that R2O2* outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.

AB - Ontologies are the fundamental building blocks of the Semantic Web and Linked Data. Reasoning is critical to ensure the logical consistency of ontologies, and to compute inferred knowledge from an ontology. It has been shown both theoretically and empirically that, despite decades of intensive work on optimising ontology reasoning algorithms, performing core reasoning tasks on large and expressive ontologies is time-consuming and resource-intensive. In this paper, we present the meta-reasoning framework R2O2* to tackle the important problems of understanding the source of TBox reasoning hardness and predicting and optimising TBox reasoning efficiency by exploiting machine learning techniques. R2O2* combines state-of-the-art OWL 2 DL reasoners as well as an efficient OWL 2 EL reasoner as components, and predicts the most efficient one by using an ensemble of robust learning algorithms including XGBoost and Random Forests. A comprehensive evaluation on a large and carefully curated ontology corpus shows that R2O2* outperforms all six component reasoners as well as AutoFolio, a robust and strong algorithm selection system.

KW - Learning

KW - Meta-reasoning

KW - Metrics

KW - Ontology

KW - OWL

KW - Performance prediction

KW - Reasoning

KW - Semantic web

UR - http://www.scopus.com/inward/record.url?scp=85068877969&partnerID=8YFLogxK

U2 - 10.1016/j.is.2019.07.002

DO - 10.1016/j.is.2019.07.002

M3 - Article

VL - 87

JO - Information Systems

JF - Information Systems

SN - 0306-4379

M1 - 101412

ER -