University of Maryland researchers have developed the Cloud Oriented Subgraph Identification (COSI) program, an algorithm that supports subgraph pattern matching in very large social networks containing billions of links. COSI makes it possible to split a social network into a set of nearly independent, relatively small subnetworks, each of which is stored on a computer in a cloud computing cluster to limit the probability that a query pattern will need to access two nodes.
The researchers say that during testing COSI was able to efficiently answer queries to social network databases containing more than a billion edges. "An innovative mix of cloud computing and smart thinking, COSI shows how exact social network pattern matching on complex query patterns can be efficiently implemented," says Maryland professor V.S. Subrahmanian.
From UM Newsdesk
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA