Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph

Abstract In recent years, hypergraph neural networks have achieved remarkable success in tasks such as node classification, link prediction, and graph classification, thanks to their powerful computational capabilities. However, most existing hypergraph neural networks are restricted to singlelayer...

Full description

Saved in:
Bibliographic Details
Main Authors: Libing Bai, Feng Hu, Chunyang Tang, Zhangyu Mei, Chuang Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-08594-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235042390245376
author Libing Bai
Feng Hu
Chunyang Tang
Zhangyu Mei
Chuang Liu
author_facet Libing Bai
Feng Hu
Chunyang Tang
Zhangyu Mei
Chuang Liu
author_sort Libing Bai
collection DOAJ
description Abstract In recent years, hypergraph neural networks have achieved remarkable success in tasks such as node classification, link prediction, and graph classification, thanks to their powerful computational capabilities. However, most existing hypergraph neural networks are restricted to singlelayer hypergraph, making it challenging to effectively capture the intricate intra-layer higher-order relationships and inter-layer interactions in multilayer hypergraph. Furthermore, these methods typically embed hypergraph features in Euclidean space, which often results in significant distortions when dealing with hypernetworks exhibiting scale-free properties or hierarchical structures. Recently, hyperbolic geometric representation learning has emerged as an effective approach to alleviate such embedding distortions. Building on this foundation, we propose a novel Hyperbolic Multi-channel HyperGraph convolutional Neural Network (HMHGNN). Specifically, a multilayer hypergraph model is first constructed based on singlelayer hypergraphs. Then, a multi-channel convolution mechanism is introduced, which integrates hypergraph’s derivative graph, hypergraph’s line graph, and hyperbolic hypergraph convolution. Subsequently, Euclidean features are mapped to hyperbolic space, and feature transformations are performed within the hyperbolic space. To evaluate the performance of the proposed model, extensive experiments were conducted on three datasets: a scientific collaboration multilayer hypernetwork, a citation multilayer hypernetwork, and a biological multilayer hypernetwork. The experimental results demonstrate that HMHGNN significantly outperforms traditional hypergraph and hyperbolic neural network models in node classification and link prediction tasks. These findings underscore the superior generalization capability and robustness of our model, offering valuable insights into the modeling and analysis of multilayer hypergraph.
format Article
id doaj-art-fac60b0106424e1a813654fec2d3e741
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-fac60b0106424e1a813654fec2d3e7412025-08-20T04:02:55ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-08594-yHyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraphLibing Bai0Feng Hu1Chunyang Tang2Zhangyu Mei3Chuang Liu4Computer College of Qinghai Normal UniversityComputer College of Qinghai Normal UniversityComputer College of Qinghai Normal UniversitySchool of Computer Science, Qufu Normal UniversityAlibaba Research Center for Complexity Sciences, Hangzhou Normal UniversityAbstract In recent years, hypergraph neural networks have achieved remarkable success in tasks such as node classification, link prediction, and graph classification, thanks to their powerful computational capabilities. However, most existing hypergraph neural networks are restricted to singlelayer hypergraph, making it challenging to effectively capture the intricate intra-layer higher-order relationships and inter-layer interactions in multilayer hypergraph. Furthermore, these methods typically embed hypergraph features in Euclidean space, which often results in significant distortions when dealing with hypernetworks exhibiting scale-free properties or hierarchical structures. Recently, hyperbolic geometric representation learning has emerged as an effective approach to alleviate such embedding distortions. Building on this foundation, we propose a novel Hyperbolic Multi-channel HyperGraph convolutional Neural Network (HMHGNN). Specifically, a multilayer hypergraph model is first constructed based on singlelayer hypergraphs. Then, a multi-channel convolution mechanism is introduced, which integrates hypergraph’s derivative graph, hypergraph’s line graph, and hyperbolic hypergraph convolution. Subsequently, Euclidean features are mapped to hyperbolic space, and feature transformations are performed within the hyperbolic space. To evaluate the performance of the proposed model, extensive experiments were conducted on three datasets: a scientific collaboration multilayer hypernetwork, a citation multilayer hypernetwork, and a biological multilayer hypernetwork. The experimental results demonstrate that HMHGNN significantly outperforms traditional hypergraph and hyperbolic neural network models in node classification and link prediction tasks. These findings underscore the superior generalization capability and robustness of our model, offering valuable insights into the modeling and analysis of multilayer hypergraph.https://doi.org/10.1038/s41598-025-08594-y
spellingShingle Libing Bai
Feng Hu
Chunyang Tang
Zhangyu Mei
Chuang Liu
Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
Scientific Reports
title Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
title_full Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
title_fullStr Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
title_full_unstemmed Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
title_short Hyperbolic multi-channel hypergraph convolutional neural network based on multilayer hypergraph
title_sort hyperbolic multi channel hypergraph convolutional neural network based on multilayer hypergraph
url https://doi.org/10.1038/s41598-025-08594-y
work_keys_str_mv AT libingbai hyperbolicmultichannelhypergraphconvolutionalneuralnetworkbasedonmultilayerhypergraph
AT fenghu hyperbolicmultichannelhypergraphconvolutionalneuralnetworkbasedonmultilayerhypergraph
AT chunyangtang hyperbolicmultichannelhypergraphconvolutionalneuralnetworkbasedonmultilayerhypergraph
AT zhangyumei hyperbolicmultichannelhypergraphconvolutionalneuralnetworkbasedonmultilayerhypergraph
AT chuangliu hyperbolicmultichannelhypergraphconvolutionalneuralnetworkbasedonmultilayerhypergraph