2014 IEEE 30th International Conference on Data Engineering 2014
DOI: 10.1109/icde.2014.6816640
|View full text |Cite
|
Sign up to set email alerts
|

Query optimization of distributed pattern matching

Abstract: Abstract-Greedy algorithms for subgraph pattern matching operations are often sufficient when the graph data set can be held in memory on a single machine. However, as graph data sets increasingly expand and require external storage and partitioning across a cluster of machines, more sophisticated query optimization techniques become critical to avoid explosions in query latency. In this paper, we introduce several query optimization techniques for distributed graph pattern matching. These techniques include (… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
11
0
2

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 23 publications
(13 citation statements)
references
References 33 publications
0
11
0
2
Order By: Relevance
“…Rather, they would like to perform the graph analytics (with comparable performance) directly with the relational engine, without the expensive step of copying data into a file system (or distributed storage system like HDFS), in order to be processed by a graph system, and then (possibly) back into the relational system for further processing. Indeed, some early efforts to implement graph queries in relational databases [6,7,8] have shown promise in this regard, but have typically only evaluated one or a small number of benchmarks, and not demonstrated the feasibility of implementing an efficient, general-purpose graph engine in a relational system.…”
Section: Why Relational Databases?mentioning
confidence: 99%
“…Rather, they would like to perform the graph analytics (with comparable performance) directly with the relational engine, without the expensive step of copying data into a file system (or distributed storage system like HDFS), in order to be processed by a graph system, and then (possibly) back into the relational system for further processing. Indeed, some early efforts to implement graph queries in relational databases [6,7,8] have shown promise in this regard, but have typically only evaluated one or a small number of benchmarks, and not demonstrated the feasibility of implementing an efficient, general-purpose graph engine in a relational system.…”
Section: Why Relational Databases?mentioning
confidence: 99%
“…Sun et al [37] used efficient in-memory graph exploration and massive parallel computing for subgraph matching rather than super-linear indices. Huang et al [39] introduced two optimization frameworks based on dynamic programming and cycle detection for distributed graph pattern matching and also proposed a computation reuse technique to eliminate redundant subgraph pattern matching.…”
Section: Related Workmentioning
confidence: 99%
“…In addition to the searching subgraph problem from a large number of small graphs, methods used to search a subgraph in a large graph such as a social network are also addressed [16,17,36,37,18,38,39]. Several up-to-date approaches such as GraphQL [16], SPath [17], and GADDI [18] are proposed to obtain all occurrences of a query in a large graph.…”
Section: Related Workmentioning
confidence: 99%
“…Figure 1(a) presents the schema (ontology) of live RDF graphs and Figure 1(b,c) presents the static KB to enrich the live event. To fulfil, the knowledge part of the streams, RDF stream processing [7,4,12] was introduced. RDF can be realised as directed-labelled graph model that consists of a set of triples, where each triple consists of subject(s) (vertex), predicate(p) (edge) and object(o) (vertex) ( s, p, o ).…”
Section: Introductionmentioning
confidence: 99%