CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network
This addresses the need for scalable deep learning on time-varying heterogeneous information networks, offering an inductive method that can handle new nodes and edges, which is incremental over previous non-inductive and structure-ignoring approaches.
The paper tackles the problem of inductive representation learning on temporal heterogeneous graphs, which are time-varying networks like citation networks, by proposing the CTRL model that integrates heterogeneous attention, edge-based Hawkes processes, and dynamic centrality to capture high-order topological evolution, resulting in significant performance boosts and outperforming state-of-the-art approaches on three benchmark datasets.
Inductive representation learning on temporal heterogeneous graphs is crucial for scalable deep learning on heterogeneous information networks (HINs) which are time-varying, such as citation networks. However, most existing approaches are not inductive and thus cannot handle new nodes or edges. Moreover, previous temporal graph embedding methods are often trained with the temporal link prediction task to simulate the link formation process of temporal graphs, while ignoring the evolution of high-order topological structures on temporal graphs. To fill these gaps, we propose a Continuous-Time Representation Learning (CTRL) model on temporal HINs. To preserve heterogeneous node features and temporal structures, CTRL integrates three parts in a single layer, they are 1) a \emph{heterogeneous attention} unit that measures the semantic correlation between nodes, 2) a \emph{edge-based Hawkes process} to capture temporal influence between heterogeneous nodes, and 3) \emph{dynamic centrality} that indicates the dynamic importance of a node. We train the CTRL model with a future event (a subgraph) prediction task to capture the evolution of the high-order network structure. Extensive experiments have been conducted on three benchmark datasets. The results demonstrate that our model significantly boosts performance and outperforms various state-of-the-art approaches. Ablation studies are conducted to demonstrate the effectiveness of the model design.