Abstract | ||
---|---|---|
In this paper we present and evaluate a parallel community detection algorithm derived from the state-of-the-art Louvain modularity maximization method. Our algorithm adopts a novel graph mapping and data representation, and relies on can efficient communication runtime, specifically designed for fine-grained applications executed on large-scale supercomputers. We have been able to parallelize graphs with up to 138 billion edges on 8, 192 Blue Gene/Q nodes and 1, 024 P7-IH nodes. Leveraging the convergence properties of our algorithm and the efficient implementation, we can analyze communities of large scale graphs in just a few seconds. To the best of our knowledge, this is the first parallel implementation of the Louvain algorithm that scales to these large data and processor configurations. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/IPDPS.2015.59 | 2015 IEEE International Parallel and Distributed Processing Symposium |
Keywords | Field | DocType |
scalable community detection,Louvain algorithm,parallel community detection algorithm,Louvain modularity maximization method,graph mapping,data representation,fine-grained applications,large-scale supercomputers,parallelize graphs | Convergence (routing),Graph,External Data Representation,Computer science,Blue gene,Parallel computing,Algorithm,Theoretical computer science,Maximization,Modularity,Scalability,Distributed computing | Conference |
ISSN | Citations | PageRank |
1530-2075 | 15 | 0.78 |
References | Authors | |
29 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xinyu Que | 1 | 124 | 11.81 |
Fabio Checconi | 2 | 197 | 14.03 |
Fabrizio Petrini | 3 | 2050 | 165.82 |
John A. Gunnels | 4 | 717 | 83.20 |