Dynamic network embedding survey

Since many real world networks are evolving over time, such as social and user-item networks, there increasing research efforts on dynamic network embedding in recent years. They learn node representations from a sequence of graphs but not only the latest network, for preserving both structural temporal information networks. Due to lack comprehensive investigation them, we give survey this paper. Our inspects data model, representation learning technique, evaluation application current related works derives common patterns them. Specifically, present two basic models, namely, discrete model continuous Correspondingly, summarize major categories techniques, structural-first temporal-first that adopted by most works. Then build taxonomy refines category hierarchy typical models. The popular experimental sets applications also summarized. Lastly, have discussion several distinct topics embedding.