# Deep Hypergraph Structure Learning

arXiv: https://arxiv.org/abs/2208.12547 · HTML: https://mlsanity.com/paper/2208.12547/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Hypergraph Neural Networks](https://mlsanity.com/paper/1809.09401/) (2018)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks](https://mlsanity.com/paper/2105.00956/) (2021)
- [You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks](https://mlsanity.com/paper/2106.13264/) (2021)
- [Graph Information Bottleneck for Subgraph Recognition](https://mlsanity.com/paper/2010.05563/) (2020)
- [Higher-order organization of complex networks](https://mlsanity.com/paper/1612.08447/) (2016)
- [HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs](https://mlsanity.com/paper/2010.04558/) (2020)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)

## Built on by (most cited first, 7 of 7)

- [HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation](https://mlsanity.com/paper/2411.18042/) (2024)
- [A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddings](https://mlsanity.com/paper/2212.14077/) (2022)
- [Hypergraph-enhanced Dual Semi-supervised Graph Classification](https://mlsanity.com/paper/2405.04773/) (2024)
- [LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100× Faster Inference](https://mlsanity.com/paper/2402.04296/) (2024)
- [Reconstructing short-lived particles using hypergraph representation learning](https://mlsanity.com/paper/2402.10149/) (2024)
- [Spectrally unstable nodes drive reliability failures in graph learning](https://mlsanity.com/paper/2412.14738/) (2024)
- [Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignment](https://mlsanity.com/paper/2608.29635/) (2026)

## Abstract (arXiv)

Learning on high-order correlation has shown superiority in data representation learning, where hypergraph has been widely used in recent decades. The performance of hypergraph-based representation learning methods, such as hypergraph neural networks, highly depends on the quality of the hypergraph structure. How to generate the hypergraph structure among data is still a challenging task. Missing and noisy data may lead to "bad connections" in the hypergraph structure and destroy the hypergraph-based representation learning process. Therefore, revealing the high-order structure, i.e., the hypergraph behind the observed data, becomes an urgent but important task. To address this issue, we design a general paradigm of deep hypergraph structure learning, namely DeepHGSL, to optimize the hypergraph structure for hypergraph-based representation learning. Concretely, inspired by the information bottleneck principle for the robustness issue, we first extend it to the hypergraph case, named by the hypergraph information bottleneck (HIB) principle. Then, we apply this principle to guide the hypergraph structure learning, where the HIB is introduced to construct the loss function to minimize the noisy information in the hypergraph structure. The hypergraph structure can be optimized and this process can be regarded as enhancing the correct connections and weakening the wrong connections in the training phase. Therefore, the proposed method benefits to extract more robust representations even on a heavily noisy structure. Finally, we evaluate the model on four benchmark datasets for representation learning. The experimental results on both graph- and hypergraph-structured data demonstrate the effectiveness and robustness of our method compared with other state-of-the-art methods.