DKWS: A Distributed System for Keyword Search on Massive Graphs

Due to the unstructuredness and the lack of schemas of graphs, such as knowledge graphs, social networks, and RDF graphs, keyword search for querying such graphs has been proposed. As graphs have become voluminous, large-scale distributed processing has attracted much interest from the database rese...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on knowledge and data engineering Jg. 36; H. 5; S. 1935 - 1950
Hauptverfasser: Jiang, Jiaxin, Choi, Byron, Huang, Xin, Xu, Jianliang, Bhowmick, Sourav S
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.05.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Computer networks
Distributed processing
Graphs
Keyword search
Keywords
Knowledge graphs
Knowledge representation
Parallel processing
Pipelines
Preempting
Programming
Search algorithms
Semantics
Social networks
Synchronization
Upper bound
Upper bounds
ISSN:1041-4347, 1558-2191
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Due to the unstructuredness and the lack of schemas of graphs, such as knowledge graphs, social networks, and RDF graphs, keyword search for querying such graphs has been proposed. As graphs have become voluminous, large-scale distributed processing has attracted much interest from the database research community. While there have been several distributed systems, distributed querying techniques for keyword search are still limited. This paper proposes a novel distributed keyword search system called <inline-formula><tex-math notation="LaTeX">\mathsf {DKWS}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">DKWS</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq1-3313726.gif"/> </inline-formula>. First, we present a monotonic property with keyword search algorithms that guarantees correct parallelization. Second, we present a keyword search algorithm as monotonic backward and forward search phases. Moreover, we propose new tight bounds for pruning nodes being searched. Third, we propose a notify-push paradigm and <inline-formula><tex-math notation="LaTeX">\mathsf {PINE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">PINE</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq2-3313726.gif"/> </inline-formula> programming model of <inline-formula><tex-math notation="LaTeX">\mathsf {DKWS}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">DKWS</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq3-3313726.gif"/> </inline-formula>. The notify-push paradigm allows asynchronously exchanging the upper bounds of matches across the workers and the coordinator in <inline-formula><tex-math notation="LaTeX">\mathsf {DKWS}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">DKWS</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq4-3313726.gif"/> </inline-formula>. The <inline-formula><tex-math notation="LaTeX">\mathsf {PINE}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">PINE</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq5-3313726.gif"/> </inline-formula> programming model naturally fits keyword search algorithms, as they have distinguished phases, to allow preemptive searches to mitigate staleness in a distributed system. Finally, we investigate the performance and effectiveness of <inline-formula><tex-math notation="LaTeX">\mathsf {DKWS}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">DKWS</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq6-3313726.gif"/> </inline-formula> through experiments using real-world datasets. We find that <inline-formula><tex-math notation="LaTeX">\mathsf {DKWS}</tex-math> <mml:math><mml:mi mathvariant="sans-serif">DKWS</mml:mi></mml:math><inline-graphic xlink:href="jiang-ieq7-3313726.gif"/> </inline-formula> is up to two orders of magnitude faster than related techniques, and its communication costs are 7.6 times smaller than those of other techniques.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2023.3313726