Temporal Heterogeneous Information Network Embedding

Abstract

Heterogeneous information network (HIN) embedding, learning the low-dimensional representation of multi-type nodes, has been applied widely and achieved excellent performance. However, most of the previous works focus more on static HINs or learning node embeddings within specific snapshots, and seldom attention has been paid to the whole evolution process and capturing all dynamics. In order to fill the gap of obtaining multi-type node embeddings by considering all temporal dynamics during the evolution, we propose a novel temporal HIN embedding method (THINE). THINE not only uses attention mechanism and meta-path to preserve structures and semantics in HIN but also combines the Hawkes process to simulate the evolution of the temporal network. Our extensive evaluations with various real-world temporal HINs demonstrate that THINE achieves the SOTA performance in both static and dynamic tasks, including node classification, link prediction, and temporal link recommendation.