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

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 fea...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2019-01, Vol.163, p.214-226
Main Authors: Mantle, Matthew, Batsakis, Sotirios, Antoniou, Grigoris
Format: Article
Language:English
Subjects:
Calculus
Current distribution
Datasets
Distributed computing
Expert systems
Graphs
Knowledge graphs
Networks
Parallel computing
Qualitative reasoning
Reasoning
Temporal logic
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2018.08.035