Anchor link prediction across social networks based on multiple consistency

Abstract

With the development of social applications, users began to participate in multiple online social networks. If the same user in different social networks can be identified, it can provide powerful help for cross-platform recommendation, information diffusion, etc. Traditional methods use interlayer or intralayer structures alone for anchor link prediction and lack the comprehensive utilization of interlayer and intralayer structures. Therefore, this paper proposes an anchor link prediction method based on multiple consistency (MC). It uses interlayer structure information in an iterative manner and intralayer structure information through network representation learning. When using the intralayer structural information, a matrix factorization-based network representation learning method is used to learn embedding vectors that contain global structural features of nodes. A radial basis neural network is then trained as a mapping function to map embedding vectors in different spaces to the same space. Finally, the anchor links between node pairs are predicted by considering the interlayer and intralayer structures together. Experiments in several real networks show that our method generally outperforms the current approach.