Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis 2017
DOI: 10.1145/3126908.3126971
|View full text |Cite
|
Sign up to set email alerts
|

Scaling betweenness centrality using communication-efficient sparse matrix multiplication

Abstract: Betweenness centrality (BC) is a crucial graph problem that measures the signi cance of a vertex by the number of shortest paths leading through it. We propose Maximal Frontier Betweenness Centrality (MFBC): a succinct BC algorithm based on novel sparse matrix multiplication routines that performs a factor of p 1/3 less communication on p processors than the best known alternatives, for graphs with n vertices and average degree k = n/p 2/3 . We formulate, implement, and prove the correctness of MFBC for weight… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
49
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
4
3
2

Relationship

1
8

Authors

Journals

citations
Cited by 73 publications
(49 citation statements)
references
References 44 publications
0
49
0
Order By: Relevance
“…Additional study appears in Solomonik et al [27] and in Azad et al [4]. The latter proposes algorithms of various types of dimensionality and also employ permutations on the input matrices.…”
Section: Related Workmentioning
confidence: 99%
“…Additional study appears in Solomonik et al [27] and in Azad et al [4]. The latter proposes algorithms of various types of dimensionality and also employ permutations on the input matrices.…”
Section: Related Workmentioning
confidence: 99%
“…In addition, Solomonik et al (2017) have proposed a parallel BC algorithm for weighted graphs based on novel sparse matrix multiplication routines that has achieved impressive performance, which may provide further inspiration for accelerating our algorithm. We may also consider implementing a GPU algorithm for processing dynamic networks.…”
Section: Resultsmentioning
confidence: 99%
“…We strongly believe that SlimSell can be used to accelerate other graph algorithms, for example schemes for solving Betweenness Centrality [35]. Potential speedups can be much higher because BFS is a data-driven scheme with different memory access patterns across iterations while many algorithms (e.g., Pagerank) have identical communication patterns in each superstep.…”
Section: Discussionmentioning
confidence: 99%