DKWS: A Distributed System for Keyword Search on Massive Graphs (Extended Abstract)

Jiaxin Jiang, Byron Choi, Xin Huang, Jianliang Xu, Sourav S Bhowmick

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Addressing the complexities of querying unstructured graphs such as knowledge graphs and social networks, this paper introduces D KWS, a novel distributed keyword search system. Leveraging a monotonic property, we ensure correct parallelization of our advanced keyword search algorithm, which incorporates tight pruning bounds and is divided into monotonic backward and forward search phases. The system is further augmented by the notify-push paradigm and the PINE programming model, facilitating asynchronous communication and preemptive searches to mitigate staleness in distributed environments. Extensive experiments on real-world datasets demonstrate DKWS's performance advantage, being up to two orders of magnitude faster and incurring 7.6 times lower communication costs than the existing systems.
Original languageEnglish
Title of host publication2024 IEEE 40th International Conference on Data Engineering (ICDE)
PublisherIEEE
Pages5689-5690
Number of pages2
ISBN (Electronic)9798350317152
ISBN (Print)9798350317169
DOIs
Publication statusPublished - 13 May 2024
Event40th IEEE International Conference on Data Engineering, ICDE 2024 - Kinepolis Jaarbeurs theater, Utrecht, Netherlands
Duration: 13 May 202417 May 2024
https://icde2024.github.io/papers.html (Link to conference's schedule )
https://icde2024.github.io/index.html (Conference's website)
https://ieeexplore.ieee.org/xpl/conhome/10597630/proceeding (Conference's proceeding)

Publication series

NameProceedings - International Conference on Data Engineering
ISSN (Print)1084-4627
ISSN (Electronic)2375-0286

Conference

Conference40th IEEE International Conference on Data Engineering, ICDE 2024
Country/TerritoryNetherlands
CityUtrecht
Period13/05/2417/05/24
Internet address

Fingerprint

Dive into the research topics of 'DKWS: A Distributed System for Keyword Search on Massive Graphs (Extended Abstract)'. Together they form a unique fingerprint.

Cite this