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

arXiv: https://arxiv.org/abs/2405.08013 · HTML: https://mlsanity.com/paper/2405.08013/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 11 May 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications](https://mlsanity.com/paper/1709.07604/) (2017)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning](https://mlsanity.com/paper/2105.09111/) (2021)
- [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020)
- [Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer](https://mlsanity.com/paper/2108.06625/) (2021)
- [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022)
- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [Temporal Network Embedding with Micro- and Macro-dynamics](https://mlsanity.com/paper/1909.04246/) (2019)
- [Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs](https://mlsanity.com/paper/2104.02228/) (2021)
- [TREND: TempoRal Event and Node Dynamics for Graph Representation Learning](https://mlsanity.com/paper/2203.14303/) (2022)

## Built on by (most cited first, 2 of 2)

- [THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model](https://mlsanity.com/paper/2607.27303/) (2026)
- [Temporal Heterogeneous Graph Pretraining for Relational Deep Learning](https://mlsanity.com/paper/2609.35219/) (2026)

## Abstract (arXiv)

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 heterogeneous attention unit that measures the semantic correlation between nodes, 2) a edge-based Hawkes process to capture temporal influence between heterogeneous nodes, and 3) 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.