Hierarchical community‐discovery algorithm combining core nodes and three‐order structure model

Abstract

AbstractA community structure in a complex network often exhibits hierarchical characteristics. Current hierarchical community‐discovery algorithms generally consider a single node as a community during the initial stage. This approach leads to over‐fine clustering granularity, too‐deep clustering levels, and other issues. Therefore, this article proposes a hierarchical community‐discovery algorithm that combines the core nodes and the three‐order structure model. Between neighboring nodes, there is a first‐order structure. The core node is identified based on its influence, and the similarity between the core node and its neighboring nodes is defined as the second‐order structure. The nodes satisfying the second‐order structure are then formed into a friend circle. The similarity between friend circles is defined as the third‐order structure. According to this structure, the friend circles are construed as a hierarchical clustering tree (HCT) where one HCT represents a community. The HCT built by this algorithm has relatively fewer levels and exhibits a flat feature. Experimental results on both artificial and real networks show that the algorithm performs well on various indicators. Additionally, the algorithm exhibits near‐linear time complexity.