Local community discovery algorithm based on subgraph structure

Local community discovery algorithms usually select seed nodes for community discovery. Aiming at the problem of insufficient effectiveness when selecting seed nodes in existing overlapping community discovery algorithms, a local community discovery algorithm based on subgraph structure (Subgragh Structure Based Overlapping Community Detection) is proposed. , SUSBOCD). This algorithm proposes a new node importance metric, which not only considers the number of neighbors of a node, but also considers the closeness of the links between neighbors. First, select the unvisited and most important node and the neighbor node that is most similar to it, merge the two nodes and their common neighbor nodes to form an initial seed subgraph, and the process iteratively runs until all nodes are visited; secondly , Perform similarity judgments based on the neighborhood information of the seed subgraphs. If they are similar, merge them to form an initial community structure. Continue to expand the process until all seed subg