Semi-supervised dynamic community detection based on non-negative matrix factorization

Abstract

How to effectively combine the network structures on different time points was the key and difficulty to affect the performance of detection algorithms. Based on this, a semi-supervised dynamic community algorithm SDCD based on non-negative matrix factorization, which effectively extracted the historical stability structure unit firstly, and then use it as a regularization item supervision of nonnegative matrix decomposition, to guide the network community detection on current moment. Experiments on the real network dat sets show that the method has a higher community detection quality compared with existing methods, which can accurately mine the relationship among different time, and explore network evolution and the law of development more adva geously.

Keywords

• semi-supervised;dynamic;community detection;on-negative matrix factorization