GraphScope
Top Cited Papers
- 12 August 2007
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 687-696
- https://doi.org/10.1145/1281192.1281266
Abstract
How can we find communities in dynamic networks of socialinteractions, such as who calls whom, who emails whom, or who sells to whom? How can we spot discontinuity time-points in such streams of graphs, in an on-line, any-time fashion? We propose GraphScope, that addresses both problems, using information theoretic principles. Contrary to the majority of earlier methods, it needs no user-defined parameters. Moreover, it is designed to operate on large graphs, in a streaming fashion. We demonstrate the efficiency and effectiveness of our GraphScope on real datasets from several diverse domains. In all cases it produces meaningful time-evolving patterns that agree with human intuition.Keywords
This publication has 12 references indexed in Scilit:
- Group formation in large social networksPublished by Association for Computing Machinery (ACM) ,2006
- Graphs over timePublished by Association for Computing Machinery (ACM) ,2005
- Compressing Bitmap Indices by Data ReorganizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Online Analysis of Community Evolution in Data StreamsPublished by Society for Industrial & Applied Mathematics (SIAM) ,2005
- Towards parameter-free data miningPublished by Association for Computing Machinery (ACM) ,2004
- Fully automatic cross-associationsPublished by Association for Computing Machinery (ACM) ,2004
- Graph-based anomaly detectionPublished by Association for Computing Machinery (ACM) ,2003
- Information-theoretic co-clusteringPublished by Association for Computing Machinery (ACM) ,2003
- Multilevelk-way Partitioning Scheme for Irregular GraphsJournal of Parallel and Distributed Computing, 1998
- A Universal Prior for Integers and Estimation by Minimum Description LengthThe Annals of Statistics, 1983