A Multi-agent Genetic Algorithm for Local Community Detection by Extending the Tightest Nodes

Finding local community structure is an appealing problem that has attracted increasing attentions. Currently, it is unrealistic to get the complete information from graphs that are too large or evolve quickly. Moreover, in many real situations, we are only interested in the local community structure of networks, but not the whole network, because the local community structures can provide us much micro analysis, which is complementary to the macroscopic analysis. Most existing methods for local community detection which are based on the source nodes are sensitive to the position of source nodes. Thus, in this paper, a new multi-agent genetic algorithm (MAGA) is proposed to find local community (LC) based on the tightest nodes rather than the given source node, which is termed as MAGA-LC. MAGA-LC first finds a set of tightest nodes, and then extends the tightest nodes to get a local community. In the experiments on synthetic and real networks, MAGA-LC can get a high F-Measure score and is quite effective and flexible in identifying local communities, and is robust to the positions of source nodes.