Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

• URL: http://arxiv.org/abs/2606.09051v1
• Date: Mon, 08 Jun 2026 05:40:19 GMT
• Title: Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
• Abstract summary: This work pioneers the study of U-Net architectures for hypergraph data, addressing the critical challenge of designing effective pooling and unpooling operations.<n>Motivated by hierarchical clustering, we propose to construct the pooling and unpooling operators all at once by cutting the clustering dendrogram at different granularities.<n>Unlike existing pooling methods that risk local structural damage through a sequential learning procedure, our PHPool operators are designed in a global and parallel manner to ensure fidelity to the original hypergraph structure.
• Score: 11.63193730379261
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutions have successfully transitioned from image processing to the complex realm of non-Euclidean higher-order domains, particularly in hypergraphs. Despite the success in convolution, the exploration of a popular architecture named U-Net remains largely unexplored for hypergraph data due to the lack of well-defined pooling and unpooling operations. This work pioneers the study of U-Net architectures for hypergraph data, addressing the critical challenge of designing effective pooling and unpooling operations that retain maximal structural information from the input hypergraph. Motivated by hierarchical clustering, we propose to construct the pooling and unpooling operators all at once by cutting the clustering dendrogram at different granularities, named the Parallel Hierarchical Pooling (PHPool) and Unpooling (PHUnpool) operators. Unlike existing pooling methods that risk local structural damage through a sequential learning procedure, our PHPool operators are designed in a global and parallel manner to ensure fidelity to the original hypergraph structure with efficient computation while the PHUnpool operators are tailored to perform inverse operations of the PHPools for hypergraph reconstruction. We validate our model through hypergraph reconstruction simulation, hypergraph classification, and node-level anomaly detection, where it demonstrates superior performance over existing state-of-the-art graph and hypergraph deep learning methods.

Related papers

• Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers [22.641550077885686]
  Looped Transformers have shown exceptional neural algorithmic reasoning capability in traditional graph algorithms.<n>We extend the Loop Transformer architecture's neural algorithmic reasoning capability to simulate hypergraph algorithms.
  arXiv  Detail & Related papers  (2025-01-18T07:58:45Z)
• Hypergraph Transformer for Semi-Supervised Classification [50.92027313775934]
  We propose a novel hypergraph learning framework, HyperGraph Transformer (HyperGT) HyperGT uses a Transformer-based neural network architecture to effectively consider global correlations among all nodes and hyperedges. It achieves comprehensive hypergraph representation learning by effectively incorporating global interactions while preserving local connectivity patterns.
  arXiv  Detail & Related papers  (2023-12-18T17:50:52Z)
• Hypergraph Echo State Network [0.0]
  A hypergraph as a generalization of graphs records higher-order interactions among nodes, yields a more flexible network model, and allows non-linear features for a group of nodes. We propose a hypergraph echo state network (HypergraphESN) as a generalization of graph echo state network (GraphESN) for efficient processing of hypergraph-structured data.
  arXiv  Detail & Related papers  (2023-10-16T08:35:23Z)
• From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
  We present an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings. We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
  arXiv  Detail & Related papers  (2023-06-16T04:40:59Z)
• Higher-order Clustering and Pooling for Graph Neural Networks [77.47617360812023]
  Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks. HoscPool is a clustering-based graph pooling operator that captures higher-order information hierarchically. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure.
  arXiv  Detail & Related papers  (2022-09-02T09:17:10Z)
• Equivariant Hypergraph Diffusion Neural Operators [81.32770440890303]
  Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data. This work proposes a new HNN architecture named ED-HNN, which provably represents any continuous equivariant hypergraph diffusion operators. We evaluate ED-HNN for node classification on nine real-world hypergraph datasets.
  arXiv  Detail & Related papers  (2022-07-14T06:17:00Z)
• Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs [59.71134113268709]
  We present General Hypergraph Spectral Convolution(GHSC), a general learning framework that can handle EDVW and EIVW hypergraphs. In this paper, we show that the proposed framework can achieve state-of-the-art performance. Experiments from various domains including social network analysis, visual objective classification, protein learning demonstrate that the proposed framework can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-31T10:46:47Z)
• HyperSF: Spectral Hypergraph Coarsening via Flow-based Local Clustering [9.438207505148947]
  We propose an efficient spectral hypergraph coarsening scheme (HyperSF) for preserving the original spectral (structural) properties of hypergraphs. Our results show that the proposed hypergraph coarsening algorithm can significantly improve the multi-way conductance of hypergraph clustering.
  arXiv  Detail & Related papers  (2021-08-17T22:20:23Z)
• Residual Enhanced Multi-Hypergraph Neural Network [26.42547421121713]
  HyperGraph Neural Network (HGNN) is the de-facto method for hypergraph representation learning. We propose the Residual enhanced Multi-Hypergraph Neural Network, which can fuse multi-modal information from each hypergraph effectively.
  arXiv  Detail & Related papers  (2021-05-02T14:53:32Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.