Social Trust Network Embedding with Hash and Graphlet

Social trust network embedding is a useful way for efficient social trust network analysis. To get more expressive representations, the latent feature and node role feature should be preserved. In many cases, the dimension of latent feature can be large, thus latent feature has storage problem with the scale of networks increasing. As hash has a good performance on compressing, we use hash to reduce the memory needed for storing latent feature. Graphlets are useful statistics for modeling the node role. Overall, in this study, we propose a novel social trust network embedding method with the concepts of hash and graphlet (STNH). Neither of them has been researched for social trust networks in prior studies. We evaluate STNH on five realworld social trust networks with respect to the downstream task of link prediction. The results demonstrate the efficacy of STNH.