# Heterogeneous Temporal Hypergraph Neural Network

arXiv: https://arxiv.org/abs/2506.17312 · HTML: https://mlsanity.com/paper/2506.17312/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 18 Jun 2025.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks](https://mlsanity.com/paper/2105.00956/) (2021)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [Dynamic Graph Neural Networks for Sequential Recommendation](https://mlsanity.com/paper/2104.07368/) (2021)
- [Heterogeneous Hypergraph Embedding for Graph Classification](https://mlsanity.com/paper/2010.10728/) (2020)
- [HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer](https://mlsanity.com/paper/2302.11329/) (2023)
- [Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN](https://mlsanity.com/paper/2004.01024/) (2020)
- [Heterogeneous Temporal Graph Neural Network](https://mlsanity.com/paper/2110.13889/) (2021)
- [Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks](https://mlsanity.com/paper/2104.07892/) (2021)
- [Hypergraph p-Laplacian: A Differential Geometry View](https://mlsanity.com/paper/1711.08171/) (2017)
- [Hypergraph Partitioning With Embeddings](https://mlsanity.com/paper/1909.04016/) (2019)
- [Abnormal Event Detection via Hypergraph Contrastive Learning](https://mlsanity.com/paper/2304.01226/) (2023)

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

- [Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics](https://mlsanity.com/paper/2509.17769/) (2025)
- [ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability](https://mlsanity.com/paper/2605.19822/) (2026)

## Abstract (arXiv)

Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal graphs (HTGs) have been proposed and have achieved successful applications in various fields. However, most existing GRL methods mainly focus on preserving the low-order topology information while ignoring higher-order group interaction relationships, which are more consistent with real-world networks. In addition, most existing hypergraph methods can only model static homogeneous graphs, limiting their ability to model high-order interactions in HTGs. Therefore, to simultaneously enable the GRL model to capture high-order interaction relationships in HTGs, we first propose a formal definition of heterogeneous temporal hypergraphs and P-uniform heterogeneous hyperedge construction algorithm that does not rely on additional information. Then, a novel Heterogeneous Temporal HyperGraph Neural network (HTHGN), is proposed to fully capture higher-order interactions in HTGs. HTHGN contains a hierarchical attention mechanism module that simultaneously performs temporal message-passing between heterogeneous nodes and hyperedges to capture rich semantics in a wider receptive field brought by hyperedges. Furthermore, HTHGN performs contrastive learning by maximizing the consistency between low-order correlated heterogeneous node pairs on HTG to avoid the low-order structural ambiguity issue. Detailed experimental results on three real-world HTG datasets verify the effectiveness of the proposed HTHGN for modeling high-order interactions in HTGs and demonstrate significant performance improvements.