Constrained Consistency Modeling for Attributed Network Embedding

Network embedding has emerged as a fundamental approach to network analysis tasks. Its main purpose is to learn a suitable mapping function to convert nodes in networks into a low-dimensional representations. The majority of existing studies concentrate solely on network topology structure. However, nodes are commonly associated with sufficient attribute information in real-world networks. Therefore, network embedding combining network topology structure and attribute information could be promisingly beneficial. Given this, we propose a novel attributed network embedding method called Consistency Constrained Attributed Network Embedding (CCANE), which preserves more complete information for nodes when learning the embedding representations. On the basis of the consistency of topology structure and node attributes, the CCANE is capable of learning the structure embeddings and attribute embeddings of nodes simultaneously, and then concatenate them to obtain the integrated vector representations. Moreover, the CCANE is scalable of dealing with large-scale of networks by decomposing the complicated optimization process into multiple sub-tasks in parallel. Experimental results testify the feasibility and superiority of the CCANE compared to the state-of-the-arts.