Results 71 to 80 of about 1,216 (173)

Hypergraph Neural Networks Based on Enclosing Subgraph Extraction for Temporal Link Prediction

IEEE Access
The Graph Neural Network (GNN) methods based on enclosing subgraph extraction have achieved excellent results in static graph link prediction tasks. However, most real-world networks are dynamic and evolve over time; the traditional models cannot capture
Ying Zhao, Xiangxu Meng, Liang Chen, Junjun Chen, Atul Sajjanhar   +4 more
doaj   +1 more source

Learning Directed Knowledge Using Higher-Ordered Neural Networks: Building a Predictive Framework

Applied Sciences
Most graph learning methods remain limited to undirected, pairwise interactions, restricting their ability to capture the multi-entity and directional relationships common in real-world systems. We propose the Directed Higher-Ordered Neural Network (HONN)
Yousra Moh Ousellam, Bikram Pratim Bhuyan, Rachida Fissoune, Galina Ivanova, Amar Ramdane-Cherif   +4 more
doaj   +1 more source

Hypergraph Convolutional Network with Multi-perspective Topology Refinement forSkeleton-based Action Recognition [PDF]

Jisuanji kexue
Since the human skeleton is a natural topological structure,graph convolutional networks(GCNs) are widely used for skeleton-based human action recognition.In recent research,skeleton sequences are represented as spatio-temporal graphs and topology graphs
HUANG Qian, SU Xinkai, LI Chang, WU Yirui
doaj   +1 more source

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

Counterfactual Explanations for Hypergraph Neural Networks

CoRR
Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, limiting their deployment in high-stakes settings. We introduce CF-HyperGNNExplainer, a counterfactual explanation method for HGNNs that identifies the minimal structural changes required to alter a model's ...
Fabiano Veglianti, Lorenzo Antonelli, Gabriele Tolomei   +2 more
openaire   +2 more sources

Hyperbolic Hypergraph Neural Networks for Hierarchical Fault Diagnosis in Rotating Machinery

Sensors
Intelligent fault diagnosis of rotating machinery is essential for ensuring the safety and reliability of industrial systems. While hypergraph neural networks (HGNNs) have recently shown promise for modeling high-order dependencies beyond pairwise graph ...
Lingzheng Pan, Kyaw Hlaing Bwar, Rifai Chai, Yuqi Wang, Boon Xian Chai   +4 more
doaj   +1 more source

Recent Advances in Hypergraph Neural Networks

Journal of the Operations Research Society of China
Abstract The growing interest in hypergraph neural networks (HGNNs) is driven by their capacity to capture the complex relationships and patterns within hypergraph structured data across various domains, including computer vision, complex networks, and natural language processing.
Mu-Rong Yang, Xin-Jian Xu
openaire   +2 more sources

Resource allocation strategy for ultra-dense Internet of things based on graph convolutional neural network

Tongxin xuebao
To address the significant issue of hidden terminal interference that severely impacted resource management in ultra-dense Internet of things (UD-IoT) environments, a deep deterministic gradient-based conflict-free resource allocation strategy using ...
HUANG Jie, LI Xingxing, YANG Fan, DING Ruijie, CAI Jieliang, YAO Fenghang, ZHANG Xin   +6 more
doaj  

Multi-Temporal Dual Polarimetric SAR Crop Classification Based on Spatial Information Comprehensive Utilization

Remote Sensing
Dual polarimetric SAR is capable of reflecting the biophysical and geometrical information of terrain with open access data availability. When it is combined with time-series observations, it can effectively capture the dynamic evolution of scattering ...
Qiang Yin, Yuming Du, Fangfang Li, Yongsheng Zhou, Fan Zhang   +4 more
doaj   +1 more source

A Research Approach to Port Information Security Link Prediction Based on HWA Algorithm

Applied Sciences
For the protection of information security, link prediction, as a basic problem of network science, has important application significance. However, most of the existing link prediction algorithms rely on the node information of the graph structure ...
Zhixin Xia, Zhangqi Zheng, Lexin Bai, Xiaolei Yang, Yongshan Liu   +4 more
doaj   +1 more source