Results 81 to 90 of about 1,404 (207)

Heterogeneous Temporal Hypergraph Neural Network

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal graphs (HTGs) have been proposed and have achieved successful applications in various fields.
Huan Liu 0001, Pengfei Jiao, Mengzhou Gao 0001, Chaochao Chen 0001, Di Jin 0001   +4 more
openaire   +2 more sources

A Two‐Stage SlowFast‐YE Network for Robust Recognition of Crew Irregularities on the Bridge

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
Innovative network structure: Our proposed SlowFast‐YE network is a real‐time, robust two‐stage network designed specifically for identifying various crew irregularities on ship bridges. Key technologies: The incorporation of Softpool and EPSA techniques enhances cross‐scale feature extraction in complex ship bridge scenes.
Deshan Chen, Long Jiang, Liang Fan, Di Zhang   +3 more
wiley   +1 more source

Equivariant Hypergraph Diffusion Neural Operators

, 2023
Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data and further solve relevant prediction tasks built upon such higher-order relations.
Liu, Yunyu, Wang, Peihao, Yang, Shenghao, Wang, Zhangyang, Li, Pan   +4 more
core  

Multiresolution Hypergraph Neural Network for Intelligent Fault Diagnosis

, 2022
Intelligent fault diagnosis has made significant progress, thanks to machine learning, particularly deep-learning algorithms. However, most machine-learning algorithms treat samples as independent and ignore the correlations between samples that contain ...
Yan,Xunshi, Zhang, Chen-an, 张陈安, 刘洋, Yan, Xunshi, Liu, Yang   +5 more
core   +1 more source

Fault diagnosis of shearer cutting unit gearbox based on improved cascaded broad learning

Gong-kuang zidonghua
The vibration monitoring data of the shearer cutting unit gearbox has a complex structure and is prone to class imbalance issues, leading to frequent false positives in traditional machine learning-based fault diagnosis methods.
LI Xin, LI Shuhua, CHEN Hao, SI Lei, WEI Dong, ZOU Xiaoyu   +5 more
doaj   +1 more source

Accounting for Work Zone Disruptions in Traffic Flow Forecasting via Multi‐Channel Attention‐Based Spatio‐Temporal Graph Convolutional Networks

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
This paper presents an approach to incorporating work zone information into network‐scale traffic prediction through graph convolutional neural networks and a novel data fusion mechanism. Contributions include the methodology itself, as well as a new data set for future research in this domain. ABSTRACT Traffic speed forecasting is an important task in
Yuanjie Lu, Shanjiang Zhu, Amarda Shehu, David Lattanzi   +3 more
wiley   +1 more source

Generalization Performance of Hypergraph Neural Networks

Proceedings of the ACM on Web Conference 2025
Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their generalization abilities in theory are less clear to us.
Yifan Wang, Gonzalo R. Arce, Guangmo Tong   +2 more
openaire   +2 more sources

Intelligent Fault Diagnosis Method Based on Hybrid Attention and Dimension‐Aligned Distillation for Rotating Machinery

IET Signal Processing, Volume 2026, Issue 1, 2026.
Intelligent fault diagnosis (IFD) of rotating machinery is critical for ensuring industrial safety and reliability. However, existing deep learning‐based IFD methods face three core challenges: suboptimal feature discrimination of single attention mechanisms, high computational cost limiting edge deployment, and class imbalance bias leading to ...
Chuanyan Wu, Zhiguo Yu, Bentao Lin, Biao Yu, Qinyu Jiang, Huanghe Zhang, Rui Gao, Qifan Yang, Rui Song, Junlin Hu   +9 more
wiley   +1 more source

Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks

, 2023
Hypergraph Neural Networks (HGNNs) have been successfully applied in various hypergraph-related tasks due to their excellent higher-order representation capabilities. Recent works have shown that deep learning models are vulnerable to adversarial attacks.
Zhao, Haixing, Ye, Zhonglin, Wang, Zhaoyang, Chen, Yang, Picek, Stjepan   +4 more
core  

EasyHypergraph: an open-source software for fast and memory-saving analysis and learning of higher-order networks

Humanities & Social Sciences Communications
Higher-order relationships exist widely across different disciplines. In the realm of real-world systems, significant interactions involving multiple entities are common.
Bodian Ye, Min Gao, Xiu-Xiu Zhan, Xinlei He, Zi-Ke Zhang, Qingyuan Gong, Xin Wang, Yang Chen   +7 more
doaj   +1 more source