Complex networks considering both positive and negative links have gainedconsiderable attention during the past several years. Community detection isone of the main challenges for complex network analysis. Most of the existingalgorithms for community detection in a signed network aim at providing ahard-partition of the network where any node should belong to a community ornot. However, they cannot detect overlapping communities where a node isallowed to belong to multiple communities. The overlapping communities widelyexist in many real world networks. In this paper, we propose a signedprobabilistic mixture (SPM) model for overlapping community detection in signednetworks. Compared with the existing models, the advantages of our methodologyare (i) providing soft-partition solutions for signed networks; (ii) providingsoft-memberships of nodes. Experiments on a number of signed networks show thatour SPM model: (i) can identify assortative structures or disassortativestructures as the same as other state-of-the-art models; (ii) can detectoverlapping communities; (iii) outperform other state-of-the-art models atshedding light on the community detection in synthetic signed networks.
展开▼
