CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network

TL;DR

CTRL is a novel continuous-time representation learning model for temporal heterogeneous information networks that captures node features, temporal influences, and node importance to improve dynamic network understanding.

Contribution

The paper introduces CTRL, a new inductive model that integrates heterogeneous attention, Hawkes processes, and dynamic centrality for temporal HINs, addressing limitations of previous methods.

Findings

CTRL outperforms state-of-the-art approaches on benchmark datasets.

The model effectively captures high-order structural evolution.

Ablation studies confirm the importance of each component.

Abstract

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.