@inproceedings{8cbfdb4b1f8746cfa07443cd4bd3ad94,
title = "A semi-clustering scheme for high performance PageRank on Hadoop",
abstract = "As global Internet business has been evolving, large-scale graphs are becoming popular. PageRank computation on the large-scale graphs using Hadoop with default data partitioning method suffers from poor performance because Hadoop scatters even a set of directly connected vertices to arbitrary multiple nodes. In this paper we propose a semi-clustering scheme to address this problem and improve the performance of PageRank on Hadoop. Our scheme divides a graph into a set of semi-clusters, each of which consists of connected vertices, and assigns a semi-cluster to a single data partition in order to reduce the cost of data exchange between nodes during the computation of PageRank. The semi-clusters are merged and split before the PageRank computation, in order to evenly distribute a large-scale graph into a number of data partitions. Our semi-clustering scheme drastically improves the performance: total elapsed time including the cost of the semi-clustering computation reduced by up to 36\%. Furthermore, the effectiveness of our scheme increases as the size of the graph increases.",
keywords = "Hadoop, Large-scale graph analysis, PageRank, Semi-clustering",
author = "Seungtae Hong and Jeonghoon Lee and Jaewoo Chang and Choi, \{Dong Hoon\}",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.; 33rd International Conference on Conceptual Modeling, ER 2014 Workshops, ENMO, MoBiD, MReBA, QMMQ, SeCoGIS, WISM, and ER Demos ; Conference date: 27-10-2014 Through 29-10-2014",
year = "2014",
doi = "10.1007/978-3-319-12256-4\_4",
language = "English",
series = "Lecture Notes in Computer Science",
publisher = "Springer Verlag",
pages = "35--44",
editor = "Marta Indulska and Sandeep Purao",
booktitle = "Advances in Conceptual Modeling - ER 2014 Workshops, ENMO, MoBiD, MReBA, QMMQ, SeCoGIS, WISM, and ER Demos, Proceedings",
}