Local community detection method based on similarity

Abstract

The invention relates to a local community detection method based on similarity, namely an-NSA (Node Similarity based Algorithm). The method is an efficient and stable local community detection methodbased on similarity, and the implementation process of the method comprises two stages, namely, the first stage of constructing an initial community structure of a network, the second stage of optimizing the initial community structure, and merging some small and sparse communities to obtain a final community structure. The method can solve the problem that a global method cannot be suitable fora large-scale network due to low efficiency, and can solve the problems that many existing local methods are unstable in performance and poor in detection result quality. Meanwhile, the invention further provides a measurement index-common metric, the scale and the sparse degree of the communities are comprehensively measured, and the small communities can be effectively merged.

Description

technical field [0001] The invention belongs to the technical field of complex network analysis, and relates to a method for detecting community structures from complex networks, in particular to a local community detection method based on node similarity. Background technique [0002] Community structure is the most prominent structural feature of complex networks. Vertices in the network can be naturally divided into multiple groups. The connections between vertices within the same group are relatively dense, while the edges between vertices in different groups are relatively sparse. Each group is a "community". [0003] In complex networks, communities often correspond to functional units of the network. For example, the grouping of Web pages with the same theme in the WWW network; functional modules in the protein molecular interaction network, metabolic channels in the metabolic network; a group of people with common characteristics in the social network, such as scien...

AI Technical Summary

Problems solved by technology

[0042] The present invention provides an efficient and stable local community detection method based on similarity - NSA (Node Similarity based Algorithm), which can solve the problem that the global method cannot be applied to large-scale networks due to low efficiency, and can solve many existing problems. The problem of unstable performance and poor quality of detection results of local methods

Images