Memory Efficient Edge Addition Designs for Large and Dynamic Social Networks

The availability of large volumes of social network data from a variety of social and socio-technical networks has greatly increased. These networks provide critical insights into understanding various domains including business, healthcare, and disaster management. The relationships and interaction...

Full description

Saved in:
Bibliographic Details
Published in:2021 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) pp. 975 - 984
Main Authors: Santos, Eunice E., Murugappan, Vairavan, Korah, John
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2021
Subjects:
Anytime anywhere algorithms
Conferences
Disaster management
Distributed processing
Graph algorithms and analysis
Heuristic algorithms
Large-scale dynamic social network analysis
Medical services
Memory efficient graph algorithms
Memory management
Parallel/Distribated algorithms
Social networking (online)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The availability of large volumes of social network data from a variety of social and socio-technical networks has greatly increased. These networks provide critical insights into understanding various domains including business, healthcare, and disaster management. The relationships and interactions between different entities represented in most of these data sources are constantly evolving. Graph processing and analysis methodologies that can effectively integrate data changes while minimizing recomputations are needed to handle these dynamic networks. In addition, the size of these information sources is constantly increasing, therefore we need designs that can perform analysis that are memory efficient in order to address resource constraints. In this paper, we show how our anytime anywhere framework can be used to construct memory-efficient closeness centrality algorithms. In particular, we will show how dynamic edge additions can be efficiently handled in the proposed scheme.
DOI:10.1109/IPDPSW52791.2021.00155