Journal
APPLIED INTELLIGENCE
Volume 44, Issue 3, Pages 621-633Publisher
SPRINGER
DOI: 10.1007/s10489-015-0716-4
Keywords
Signed network; Community detection; Particle swarm optimization; Multiobjective optimization
Categories
Funding
- Science Project of Yulin City [Gy13-15, Ny13-10]
- Scientific Research Program of Department of Education of Shaanxi Province [14JK1859]
Ask authors/readers for more resources
Signed graphs or networks are effective models for analyzing complex social systems. Community detection from signed networks has received enormous attention from diverse fields. In this paper, the signed network community detection problem is addressed from the viewpoint of evolutionary computation. A multiobjective optimization model based on link density is newly proposed for the community detection problem. A novel multiobjective particle swarm optimization algorithm is put forward to solve the proposed optimization model. Each single run of the proposed algorithm can produce a set of evenly distributed Pareto solutions each of which represents a network community structure. To check the performance of the proposed algorithm, extensive experiments on synthetic and real-world signed networks are carried out. Comparisons against several state-of-the-art approaches for signed network community detection are carried out. The experiments demonstrate that the proposed optimization model and the algorithm are promising for community detection from signed networks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available