Learning Neural Representations for Dynamic Heterogeneous Graphs

Many real-world networks, such as social networks and academic networks, contain structural heterogeneity and experience temporal evolution. However, while there has been growing literature on network representation learning, only a few have addressed the need to learn representations for dynamic heterogeneous networks. The objective of our work in this thesis is to introduce DyHNet, which learns representations for such networks and distinguishes itself from the state-of-the-art by systematically capturing different semantics, (1) local node semantics, (2) global network semantics, and (3) longer-range temporal associations between network snapshots when learning network representations. We conduct experiments consisting of the two most common downstream graph learning tasks on four real-world datasets. Our results demonstrate that the proposed method is able to show consistently better and more robust performance compared to the state-of-the-art techniques.