# Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN

arXiv: https://arxiv.org/abs/2004.01024 · HTML: https://mlsanity.com/paper/2004.01024/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [Dynamic Network Embedding Survey](https://mlsanity.com/paper/2103.15447/) (2021)
- [Reinforced Structured State-Evolution for Vision-Language Navigation](https://mlsanity.com/paper/2204.09280/) (2022)
- [TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs](https://mlsanity.com/paper/2406.09639/) (2024)
- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [Heterogeneous Temporal Graph Neural Network](https://mlsanity.com/paper/2110.13889/) (2021)
- [Continual Graph Learning: A Survey](https://mlsanity.com/paper/2301.12230/) (2023)
- [Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks](https://mlsanity.com/paper/2102.06371/) (2021)
- [CLDG: Contrastive Learning on Dynamic Graphs](https://mlsanity.com/paper/2412.14451/) (2024)
- [Robust Knowledge Adaptation for Dynamic Graph Neural Networks](https://mlsanity.com/paper/2207.10839/) (2022)
- [Instant Representation Learning for Recommendation over Large Dynamic Graphs](https://mlsanity.com/paper/2305.18622/) (2023)
- [A Survey of Link Prediction in Temporal Networks](https://mlsanity.com/paper/2502.21185/) (2025)
- [HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction](https://mlsanity.com/paper/2202.12713/) (2022)
- [Temporal Graph Network Embedding with Causal Anonymous Walks Representations](https://mlsanity.com/paper/2108.08754/) (2021)
- [Heterogeneous Temporal Hypergraph Neural Network](https://mlsanity.com/paper/2506.17312/) (2025)
- [Simple and Efficient Heterogeneous Temporal Graph Neural Network](https://mlsanity.com/paper/2510.18467/) (2025)
- [CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?](https://mlsanity.com/paper/2512.11352/) (2025)
- [ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding](https://mlsanity.com/paper/2310.04865/) (2023)
- [Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks](https://mlsanity.com/paper/2510.11903/) (2025)
- [Missing Data Estimation in Temporal Multilayer Position-aware Graph Neural Network (TMP-GNN)](https://mlsanity.com/paper/2108.03400/) (2021)
- [RHCO: A Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning for Large-scale Graphs](https://mlsanity.com/paper/2211.11752/) (2022)
- [Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction](https://mlsanity.com/paper/2307.08877/) (2023)
- [DyGSSM: Multi-view Dynamic Graph Embeddings with State Space Model Gradient Update](https://mlsanity.com/paper/2505.09017/) (2025)
- [Dynamic Heterogeneous Graph Representation Learning: A Survey](https://mlsanity.com/paper/2609.04779/) (2026)

## Abstract (arXiv)

Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification. Most of existing network embedding algorithms focus on how to learn static homogeneous networks effectively. However, networks in the real world are more complex, e.g., networks may consist of several types of nodes and edges (called heterogeneous information) and may vary over time in terms of dynamic nodes and edges (called evolutionary patterns). Limited work has been done for network embedding of dynamic heterogeneous networks as it is challenging to learn both evolutionary and heterogeneous information simultaneously. In this paper, we propose a novel dynamic heterogeneous network embedding method, termed as DyHATR, which uses hierarchical attention to learn heterogeneous information and incorporates recurrent neural networks with temporal attention to capture evolutionary patterns. We benchmark our method on four real-world datasets for the task of link prediction. Experimental results show that DyHATR significantly outperforms several state-of-the-art baselines.