# Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

arXiv: https://arxiv.org/abs/2307.03411 · HTML: https://mlsanity.com/paper/2307.03411/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 68 references that are in the map.
- First posted on arXiv 7 Jul 2023.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [A Survey on Knowledge Graph-Based Recommender Systems](https://mlsanity.com/paper/2003.00911/) (2020)
- [A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources](https://mlsanity.com/paper/2011.14867/) (2020)
- [Relation-Aware Graph Attention Network for Visual Question Answering](https://mlsanity.com/paper/1903.12314/) (2019)
- [Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification](https://mlsanity.com/paper/2104.14913/) (2021)
- [Heterogeneous Hypergraph Embedding for Graph Classification](https://mlsanity.com/paper/2010.10728/) (2020)
- [Inhomogeneous Hypergraph Clustering with Applications](https://mlsanity.com/paper/1709.01249/) (2017)
- [Heterogeneous Graph Representation Learning with Relation Awareness](https://mlsanity.com/paper/2105.11122/) (2021)
- [Self-supervised Hypergraph Representation Learning for Sociological Analysis](https://mlsanity.com/paper/2212.11440/) (2022)
- [Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation](https://mlsanity.com/paper/2103.13506/) (2021)
- [An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning](https://mlsanity.com/paper/2206.03420/) (2022)
- [SHINE: SubHypergraph Inductive Neural nEtwork](https://mlsanity.com/paper/2210.07309/) (2022)
- [Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks](https://mlsanity.com/paper/2210.17142/) (2022)

## Built on by (most cited first, 8 of 8)

- [Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs](https://mlsanity.com/paper/2404.11014/) (2024)
- [Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen](https://mlsanity.com/paper/2505.21743/) (2025)
- [Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems](https://mlsanity.com/paper/2503.10421/) (2025)
- [Exploiting Spatial-temporal Data for Sleep Stage Classification via Hypergraph Learning](https://mlsanity.com/paper/2309.02124/) (2023)
- [HyperSMOTE: A Hypergraph-based Oversampling Approach for Imbalanced Node Classifications](https://mlsanity.com/paper/2409.05402/) (2024)
- [Constraints Matrix Diffusion based Generative Neural Solver for Vehicle Routing Problems](https://mlsanity.com/paper/2603.07568/) (2026)
- [Multi-view Attention Fusion of Heterogeneous Hypergraph with Dynamic Behavioral Profiling for Personalized Learning Resource Recommendation](https://mlsanity.com/paper/2603.13310/) (2026)
- [A Network-driven Framework for Public Event Forecasting via Dynamic Interaction Network Evolution](https://mlsanity.com/paper/2608.15488/) (2026)

## Abstract (arXiv)

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with eleven state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (average 12.5% in node classification and 13.3% in link prediction) compared with recent state-of-the-art methods.