Dynamic networks are complex networks as their structures and node features change over time.However,they can better represent the real world,thus attracting the interest of researchers.Although realistic dynamic networks often exhibit changes in their patterns,the existing dynamic network models tend to classify all the snapshots as having the same pattern to learn during their em-bedding.The NS-PCN framework is proposed for this situation,which can extract the pattern infor-mation in the network efficiently according to the change of network patterns.Finally,link prediction experiments are conducted on four real datasets,and the obtained results show a significant improve-ment of the existing dynamic network embedding model in the present framework.
国家科技期刊平台
NSTL
万方数据
