• Home
  • Search
  • UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
  • Cite Icon185
  • https://doi.org/10.24963/ijcai.2021/353Copy DOI Icon

UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

  • Aug 1, 2021
  • Jing Huang +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4% to 88.8% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at https://github.com/OneForward/UniGNN.

Similar Papers
  • Dissertation

Graph neural differential equation networks for improved representation learning and robustness

  • Jan 01, 2024
  • Kai Zhao
  • Conference Article

KAFNN: A Knowledge Augmentation Framework to Graph Neural Networks

  • Jul 18, 2022
  • Bisheng Tang +3
  • Research Article
  • Citations1

Multiplex Network Representation Learning Based on Graph Neural Network

  • May 14, 2024
  • Journal of Theory and Practice of Engineering Science
  • Lianwei Li +4
  • Research Article
  • Citations83

The Vapnik–Chervonenkis dimension of graph and recursive neural networks

  • Sep 01, 2018
  • Neural Networks
  • Franco Scarselli +2
  • Research Article
  • Citations1

Revolutionizing Autonomous Parking: GNN-Powered Slot Detection for Enhanced Efficiency

  • Jan 01, 2024
  • Interdisciplinary Journal of Information, Knowledge, and Management
  • Vignesh U +1
  • Research Article
  • Citations3

Semantic graph neural network with multi-measure learning for semi-supervised classification

  • Nov 29, 2024
  • Engineering Applications of Artificial Intelligence
  • Junchao Lin +3
  • PDF
  • Research Article
  • Citations2

FICOM: an effective and scalable active learning framework for GNNs on semi-supervised node classification

  • Jul 22, 2024
  • The VLDB Journal
  • Xingyi Zhang +3
  • Research Article
  • Citations1

Interpretation of chemical reaction yields with graph neural additive network

  • Jun 10, 2025
  • Machine Learning: Science and Technology
  • Youngchun Kwon +3
  • Conference Article
  • Citations1

A Short Survey on Inductive Biased Graph Neural Networks

  • May 01, 2022
  • Yuqi Zhang +4
  • PDF
  • Research Article
  • Citations6

Towards Exploring the Limitations of Test Selection Techniques on Graph Neural Networks: An Empirical Study

  • Jul 22, 2024
  • Empirical Software Engineering
  • Xueqi Dang +7
  • Research Article
  • Citations4

Optimal graph representations and neural networks for multichannel time series data in seizure phase classification

  • Jun 04, 2025
  • Scientific Reports
  • Alan A Díaz-Montiel +2
  • Research Article
  • Citations5

Shared Growth of Graph Neural Networks via Prompted Free-Direction Knowledge Distillation.

  • Jun 01, 2025
  • IEEE transactions on pattern analysis and machine intelligence
  • Kaituo Feng +4
  • PDF
  • Research Article
  • Citations33

Graph Neural Networks With Triple Attention for Few-Shot Learning

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Hao Cheng +3
  • Research Article
  • Citations76

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

  • Jun 28, 2022
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Aosong Feng +3
  • Conference Article
  • Citations6

Graph Neural Networks for Z-DNA prediction in Genomes

  • Dec 06, 2022
  • Artem Voytetskiy +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.