Learning and Updating Node Embedding on Dynamic Heterogeneous Information Network

Heterogeneous information networks consist of multiple types of edges and nodes, which have a strong ability to represent the rich semantic of network structures. Recently, the dynamic of the heterogeneous network has been studied in many tasks such as social media analysis and recommender systems. However, existing methods mainly focus on the static network or dynamic homogeneous network, which are inefficient for modeling dynamic information in heterogeneous networks. In this paper, we propose a method named Dynamic Heterogeneous Information Network Embedding (DyHINE), which can update embeddings when the network evolves. The method contains two key designs: (1) Dynamic time-series embedding model which employs a hierarchical attention mechanism to aggregate neighbor features and uses temporal random walk to capture dynamic information; (2) Online real-time update model which efficiently captures the real-time updated embedding via a dynamic operator. Experiments on three real-world datasets demonstrate the effectiveness of our model compared with state-of-the-art methods on temporal link task.