Home // DBKDA 2016, The Eighth International Conference on Advances in Databases, Knowledge, and Data Applications // View article

Discovering the Most Dominant Nodes in Frequent Subgraphs

Authors:
Farah Chanchary
Herna Viktor
Anil Maheshwari

Keywords: Frequent subgraphs; Graph mining; Most dominant nodes; Time evolving graph.

Abstract:
Recently, there is a growing trend to utilize data mining algorithms to explore datasets being modeled using graphs. In most cases, these graphs evolve over time, thus exhibiting more complex patterns and relationships among nodes. In particular, social networks are believed to manifest the preferential attachment property which assumes that new graph nodes have a higher probability of forming links with high-degree nodes. Often, these high-degree nodes have the tendency to become the articulation points in frequent subgraphs (also known as the most dominant nodes). Thus, their identification is important, because their disappearance may have greater influence on their peer nodes. Also, exploring their properties is essential when aiming to predict future frequent patterns. In this paper, we introduce a binary classification model DetectMDN to correctly classify the most dominant nodes in frequently occurring subgraphs. A set of experimental results confirms the feasibility and accuracy of our approach.

Pages: 72 to 77

Copyright: Copyright (c) IARIA, 2016

Publication date: June 26, 2016

Published in: conference

ISSN: 2308-4332

ISBN: 978-1-61208-486-2

Location: Lisbon, Portugal

Dates: from June 26, 2016 to June 30, 2016