Results 141 to 150 of about 2,491 (218)

VLSI Hypergraph Partitioning with Deep Learning

CoRR
Partitioning is a known problem in computer science and is critical in chip design workflows, as advancements in this area can significantly influence design quality and efficiency. Deep Learning (DL) techniques, particularly those involving Graph Neural Networks (GNNs), have demonstrated strong performance in various node, edge, and graph prediction ...
Muhammad Hadir Khan, Bugra Onal, Eren Dogan, Matthew R. Guthaus   +3 more
openaire   +2 more sources

A semi-supervised fault diagnosis method based on dynamic decay learning strategy and hypergraph attention network

Advances in Mechanical Engineering
To solve the fault diagnosis difficulties in autonomous underwater vehicle (AUV) thrusters, a semi-supervised AUV fault diagnosis method based on dynamic decay learning strategy and hypergraph attention network (HGAN) is proposed.
Shuai Zheng, Hongchao Wang
doaj   +1 more source

Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing

Mathematics
To address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency.
Hongyu Lin, Shaofeng Shen, Yuchen Zhang, Renwei Xia   +3 more
doaj   +1 more source

Attention-Based Hypergraph Neural Network: A Personalized Recommendation

Applied Sciences
Personalized recommendation for online learning courses stands as a critical research topic in educational technology, where algorithmic performance directly impacts learning efficiency and user experience.
Peihua Xu, Maoyuan Zhang
doaj   +1 more source

Hypergraph node representation learning with one-stage message passing

Hypergraphs as an expressive and general structure have attracted considerable attention from various research domains. Most existing hypergraph node representation learning techniques are based on graph neural networks, and thus adopt the two-stage ...
Wang, Weiqing, Li, Yuan Fang, Yuan, Fajie, Zhou, Xin, Qu, Shilin   +4 more
core   +1 more source

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

, 2022
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL).
Shen, Yang, He, Jingrui, Chen, Tianlong, Wei, Tianxin, Wang, Zhangyang, You, Yuning   +5 more
core  

Spectral–Spatial Hypergraph Convolutional Network for Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In recent years, due to the high-order nonlinear modeling capability of hypergraph convolutional network (HGCN), it has been introduced into the field of hyperspectral image (HSI) classification.
Qingwang Wang, Fenlian Liu, Mingguo Wang, Lizhi Wang, Jiangbo Huang, Tao Shen   +5 more
doaj   +1 more source

Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

CoRR
Camera ready revision: accepted to ICLR ...
Emanuele Mule, Stefano Fiorini, Antonio Purificato, Federico Siciliano, Stefano Coniglio, Fabrizio Silvestri   +5 more
openaire   +2 more sources

HJE: Joint Convolutional Representation Learning for Knowledge Hypergraph Completion

HJE: Joint Convolutional Representation Learning for Knowledge Hypergraph ...
Zhao Li (300229), Jianxin Li (13075998), Zirui Chen (12218174), Xin Wang (91924), Chenxu Wang (420276)   +4 more
core   +1 more source

Unsupervised hyperspectral images classification using hypergraph convolutional extreme learning machines

IET Image Processing
Aiming at the problem that traditional methods are difficult to fully utilize the rich spectral information in hyperspectral images (HSI) and fail to capture the complex higher‐order relations in hyperspectral data, which leads to limited classification ...
Hongrui Zhang, Hongfei Lv, Mengke Wang, Luyao Wang, Jinhuan Xu, Fenggui Wang, Xiangdong Li   +6 more
doaj   +1 more source