Large scale distributed spatio-temporal reasoning using real-world knowledge graphs

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Most of the existing work in the field of Qualitative Spatial Temporal Reasoning (QSTR) has focussed on comparatively small constraint networks that consist of hundreds or at most thousands of relations. Recently we have seen the emergence of much larger qualitative spatial knowledge graphs that feature hundreds of thousands and millions of relations. Traditional approaches to QSTR are unable to reason over networks of such size.

In this article we describe ParQR, a parallel, distributed implementation of QSTR techniques that addresses the challenge of reasoning over large-scale qualitative spatial and temporal datasets. We have implemented ParQR using the Apache Spark framework, and evaluated our approach using both large scale synthetic datasets and real-world knowledge graphs. We show that our approach scales effectively, is able to handle constraint networks consisting of millions of relations, and outperforms current distributed implementations of QSTR.
LanguageEnglish
Pages214-226
Number of pages13
JournalKnowledge-Based Systems
Volume163
Early online date30 Aug 2018
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Electric sparks
Graph

Cite this

@article{93776ec0d900447492c6c228f5dd87e4,
title = "Large scale distributed spatio-temporal reasoning using real-world knowledge graphs",
abstract = "Most of the existing work in the field of Qualitative Spatial Temporal Reasoning (QSTR) has focussed on comparatively small constraint networks that consist of hundreds or at most thousands of relations. Recently we have seen the emergence of much larger qualitative spatial knowledge graphs that feature hundreds of thousands and millions of relations. Traditional approaches to QSTR are unable to reason over networks of such size.In this article we describe ParQR, a parallel, distributed implementation of QSTR techniques that addresses the challenge of reasoning over large-scale qualitative spatial and temporal datasets. We have implemented ParQR using the Apache Spark framework, and evaluated our approach using both large scale synthetic datasets and real-world knowledge graphs. We show that our approach scales effectively, is able to handle constraint networks consisting of millions of relations, and outperforms current distributed implementations of QSTR.",
keywords = "Distributed computing, Knowledge graphs, Parallel computing, Qualitative reasoning",
author = "Matthew Mantle and Sotirios Batsakis and Grigoris Antoniou",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.knosys.2018.08.035",
language = "English",
volume = "163",
pages = "214--226",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

TY - JOUR

T1 - Large scale distributed spatio-temporal reasoning using real-world knowledge graphs

AU - Mantle, Matthew

AU - Batsakis, Sotirios

AU - Antoniou, Grigoris

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Most of the existing work in the field of Qualitative Spatial Temporal Reasoning (QSTR) has focussed on comparatively small constraint networks that consist of hundreds or at most thousands of relations. Recently we have seen the emergence of much larger qualitative spatial knowledge graphs that feature hundreds of thousands and millions of relations. Traditional approaches to QSTR are unable to reason over networks of such size.In this article we describe ParQR, a parallel, distributed implementation of QSTR techniques that addresses the challenge of reasoning over large-scale qualitative spatial and temporal datasets. We have implemented ParQR using the Apache Spark framework, and evaluated our approach using both large scale synthetic datasets and real-world knowledge graphs. We show that our approach scales effectively, is able to handle constraint networks consisting of millions of relations, and outperforms current distributed implementations of QSTR.

AB - Most of the existing work in the field of Qualitative Spatial Temporal Reasoning (QSTR) has focussed on comparatively small constraint networks that consist of hundreds or at most thousands of relations. Recently we have seen the emergence of much larger qualitative spatial knowledge graphs that feature hundreds of thousands and millions of relations. Traditional approaches to QSTR are unable to reason over networks of such size.In this article we describe ParQR, a parallel, distributed implementation of QSTR techniques that addresses the challenge of reasoning over large-scale qualitative spatial and temporal datasets. We have implemented ParQR using the Apache Spark framework, and evaluated our approach using both large scale synthetic datasets and real-world knowledge graphs. We show that our approach scales effectively, is able to handle constraint networks consisting of millions of relations, and outperforms current distributed implementations of QSTR.

KW - Distributed computing

KW - Knowledge graphs

KW - Parallel computing

KW - Qualitative reasoning

UR - http://www.scopus.com/inward/record.url?scp=85053025476&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2018.08.035

DO - 10.1016/j.knosys.2018.08.035

M3 - Article

VL - 163

SP - 214

EP - 226

JO - Knowledge-Based Systems

T2 - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -