A Framework for Fast Community Extraction of Large-Scale Networks
- Yutaka I. Leon-Suematsu(NiCT/ATR)
- Kikuo Yuta(NiCT/ATR)
Most of the faster community extraction algorithms are based on the Clauset, Newman and Moore (CNM), which is employed for networks with sizes up to 500,000 nodes. The modification proposed by Danon, Diaz and Arenas (DDA) obtains better modularity among CNM and its variations, but there is no improvement in speed as its authors expressed. In this paper, we identify some inefficiencies in the data structure employed by former algorithms. We propose a new framework for the algorithm and a modification of the DDA to make it applicable to large-scale networks. For instance, the community extraction of a network with 1 million nodes and 5 million edges was performed in about 14 minutes in contrast to former CNM that required 45 hours (192 times the former CNM, obtaining better modularity). The scalability of our improvements is shown by applying it to networks with sizes up to 10 million nodes, obtaining the best modularity and execution time compared to the former algorithms.
Inquiries can be sent to: