Discovering global network communities based on local centralities
ACM Transactions on the Web (TWEB)
Self-organized combinatorial optimization
Expert Systems with Applications: An International Journal
Data intensive distributed computing in data aware self-organizing networks
Transactions on Computational Science XV
Finding Communities in Weighted Signed Social Networks
ASONAM '12 Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012)
| Hi-index | 0.00 |
A network community is a special sub-network that contains a group of nodes sharing similar linked patterns. A distributed network community mining problem (D-NCMP) is concerned with finding all such communities from a distributed network. A variety of applications in WWW and ad-hoc networks such as P2P and sensor networks can be formulated into DNCMPs, in which both resources and controls are distributed and/or decentralized. The problem is difficult for some existing methods to deal with because of the fact that their required global topological representations of distributed networks are hard to obtain. In this paper, we present an autonomy oriented computing (AOC) approach [15], in which the nodes and links of a distributed network are distributed among a group of autonomous agents that collectively find global communities hidden in the network. In doing so, the agents maintain only their respective local views and update them through a proposed self-organization process. The effectiveness of the AOC based approach has been validated using network examples.