User Alignment via Structural Interaction and Propagation

Anfeng Cheng, Chun-Yi Liu, Chuan Zhou, Jianlong Tan, Li Guo

Abstract: User alignment between different social networks is a fundamental issue for many applications, such as information diffusion and recommendation. In actuality, the observed anchor users are normally sparse due to the expensiveness of labeling data. Hence how to make the best use of these sparse anchor information is an important open issue. To this end, we proposed a User Alignment via Structural Interaction and Propagation (UASIP) model to capture the structural information interaction across two social networks, which exploits deep structural infor- mation to enhance the representations of users. UASIP learns vector representation by automatically keeping the consistency between this additional structural information and intrinsic structural information of the two social networks. Experiments on real-world social network datasets demonstrate the effectiveness of UASIP compared with several state-of-the-art methods.