BLADYG: A novel block-centric framework for the analysis of large dynamic graphs

Sabeur Aridhi; Alberto Montresor; Yannis Velegrakis

doi:10.1145/2915516.2915525

BLADYG: A novel block-centric framework for the analysis of large dynamic graphs

Sabeur Aridhi, Alberto Montresor, Yannis Velegrakis

BEC-INFM

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

3 Citations (Scopus)

Abstract

Recently, distributed processing of large dynamic graphs has become very popular, especially in certain domains such as social network analysis, Web graph analysis and spatial network analysis. In this context, many distributed/parallel graph processing systems have been proposed, such as Pregel, GraphLab, and Trinity. These systems can be divided into two categories: (1) vertex-centric and (2) block-centric approaches. In vertex-centric approaches, each vertex corresponds to a process, and message are exchanged among vertices. In block-centric approaches, the unit of computation is a block, a connected subgraph of the graph, and message exchanges occur among blocks. In this paper, we are considering the issues of scale and dynamism in the case of block-centric approaches. We present BLADYG, a block-centric framework that addresses the issue of dynamism in large-scale graphs. We present an implementation of BLADYG on top of AKKA framework. We experimentally evaluate the performance of the proposed framework.

Original language	English
Title of host publication	HPGP 2016 - Proceedings of the ACM Workshop on High Performance Graph Processing, Co-located with HPDC 2016
Publisher	ACM
Pages	39-42
Number of pages	4
ISBN (Electronic)	9781450343503
DOIs	https://doi.org/10.1145/2915516.2915525
Publication status	Published - 31 May 2016
MoE publication type	A4 Conference publication
Event	ACM Workshop on High Performance Graph Processing - Kyoto, Japan Duration: 31 May 2016 → 4 Jun 2016

Workshop

Workshop	ACM Workshop on High Performance Graph Processing
Abbreviated title	HPGP
Country/Territory	Japan
City	Kyoto
Period	31/05/2016 → 04/06/2016

Keywords

AKKA framework
Distributed graph processing
Dynamic graphs

Access to Document

10.1145/2915516.2915525

Cite this

@inproceedings{fcc9ee47f19345af904975d2b7455a29,

title = "BLADYG: A novel block-centric framework for the analysis of large dynamic graphs",

abstract = "Recently, distributed processing of large dynamic graphs has become very popular, especially in certain domains such as social network analysis, Web graph analysis and spatial network analysis. In this context, many distributed/parallel graph processing systems have been proposed, such as Pregel, GraphLab, and Trinity. These systems can be divided into two categories: (1) vertex-centric and (2) block-centric approaches. In vertex-centric approaches, each vertex corresponds to a process, and message are exchanged among vertices. In block-centric approaches, the unit of computation is a block, a connected subgraph of the graph, and message exchanges occur among blocks. In this paper, we are considering the issues of scale and dynamism in the case of block-centric approaches. We present BLADYG, a block-centric framework that addresses the issue of dynamism in large-scale graphs. We present an implementation of BLADYG on top of AKKA framework. We experimentally evaluate the performance of the proposed framework.",

keywords = "AKKA framework, Distributed graph processing, Dynamic graphs",

author = "Sabeur Aridhi and Alberto Montresor and Yannis Velegrakis",

year = "2016",

month = may,

day = "31",

doi = "10.1145/2915516.2915525",

language = "English",

pages = "39--42",

booktitle = "HPGP 2016 - Proceedings of the ACM Workshop on High Performance Graph Processing, Co-located with HPDC 2016",

publisher = "ACM",

address = "United States",

note = "ACM Workshop on High Performance Graph Processing, HPGP ; Conference date: 31-05-2016 Through 04-06-2016",

}

Aridhi, S, Montresor, A & Velegrakis, Y 2016, BLADYG: A novel block-centric framework for the analysis of large dynamic graphs. in HPGP 2016 - Proceedings of the ACM Workshop on High Performance Graph Processing, Co-located with HPDC 2016. ACM, pp. 39-42, ACM Workshop on High Performance Graph Processing, Kyoto, Japan, 31/05/2016. https://doi.org/10.1145/2915516.2915525

BLADYG: A novel block-centric framework for the analysis of large dynamic graphs. / Aridhi, Sabeur; Montresor, Alberto; Velegrakis, Yannis.
HPGP 2016 - Proceedings of the ACM Workshop on High Performance Graph Processing, Co-located with HPDC 2016. ACM, 2016. p. 39-42.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - BLADYG

T2 - ACM Workshop on High Performance Graph Processing

AU - Aridhi, Sabeur

AU - Montresor, Alberto

AU - Velegrakis, Yannis

PY - 2016/5/31

Y1 - 2016/5/31

N2 - Recently, distributed processing of large dynamic graphs has become very popular, especially in certain domains such as social network analysis, Web graph analysis and spatial network analysis. In this context, many distributed/parallel graph processing systems have been proposed, such as Pregel, GraphLab, and Trinity. These systems can be divided into two categories: (1) vertex-centric and (2) block-centric approaches. In vertex-centric approaches, each vertex corresponds to a process, and message are exchanged among vertices. In block-centric approaches, the unit of computation is a block, a connected subgraph of the graph, and message exchanges occur among blocks. In this paper, we are considering the issues of scale and dynamism in the case of block-centric approaches. We present BLADYG, a block-centric framework that addresses the issue of dynamism in large-scale graphs. We present an implementation of BLADYG on top of AKKA framework. We experimentally evaluate the performance of the proposed framework.

AB - Recently, distributed processing of large dynamic graphs has become very popular, especially in certain domains such as social network analysis, Web graph analysis and spatial network analysis. In this context, many distributed/parallel graph processing systems have been proposed, such as Pregel, GraphLab, and Trinity. These systems can be divided into two categories: (1) vertex-centric and (2) block-centric approaches. In vertex-centric approaches, each vertex corresponds to a process, and message are exchanged among vertices. In block-centric approaches, the unit of computation is a block, a connected subgraph of the graph, and message exchanges occur among blocks. In this paper, we are considering the issues of scale and dynamism in the case of block-centric approaches. We present BLADYG, a block-centric framework that addresses the issue of dynamism in large-scale graphs. We present an implementation of BLADYG on top of AKKA framework. We experimentally evaluate the performance of the proposed framework.

KW - AKKA framework

KW - Distributed graph processing

KW - Dynamic graphs

UR - http://www.scopus.com/inward/record.url?scp=84978924716&partnerID=8YFLogxK

U2 - 10.1145/2915516.2915525

DO - 10.1145/2915516.2915525

M3 - Conference article in proceedings

AN - SCOPUS:84978924716

SP - 39

EP - 42

BT - HPGP 2016 - Proceedings of the ACM Workshop on High Performance Graph Processing, Co-located with HPDC 2016

PB - ACM

Y2 - 31 May 2016 through 4 June 2016

ER -

BLADYG: A novel block-centric framework for the analysis of large dynamic graphs

Abstract

Workshop

Keywords

Access to Document

Other files and links

Fingerprint

Cite this