典型文献
DeepHGNN:A Novel Deep Hypergraph Neural Network
文献摘要：
With the development of deep learning,graph neural networks(GNNs)have yielded substantial results in various application fields.GNNs mainly con-sider the pair-wise connections and deal with graph-struc-tured data.In many real-world networks,the relations between objects are complex and go beyond pair-wise.Hypergraph is a flexible modeling tool to describe intric-ate and higher-order correlations.The researchers have been concerned how to develop hypergraph-based neural network model.The existing hypergraph neural networks show better performance in node classification tasks and so on,while they are shallow network because of over-smoothing,over-fitting and gradient vanishment.To tackle these issues,we present a novel deep hypergraph neural network(DeepHGNN).We design DeepHGNN by using the technologies of sampling hyperedge,residual connection and identity mapping,residual connection and identity mapping bring from graph convolutional neural networks.We evaluate DeepHGNN on two visual object datasets.The experiments show the positive effects of DeepHGNN,and it works better in visual object classific-ation tasks.
文献关键词：
中图分类号：
作者姓名：
LIN Jingjing;YE Zhonglin;ZHAO Haixing;FANG Lusheng
作者机构：
College of Computer,Qinghai Normal University,Xining 810008,China;The State Key Laboratory of Tibetan Intelligent Information Processing and Application,Xining 810008,China;Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province,Xining 810008,China;Xining Urban Vocational&Technical College,Xining 810003,China
文献出处：
引用格式：
[1]LIN Jingjing;YE Zhonglin;ZHAO Haixing;FANG Lusheng-.DeepHGNN:A Novel Deep Hypergraph Neural Network)[J].电子学报（英文）,2022(05):958-968
A类：
DeepHGNN,intric,vanishment,hyperedge,classific
B类：
Novel,Hypergraph,Neural,Network,With,development,deep,learning,neural,networks,GNNs,have,yielded,substantial,results,various,application,fields,mainly,sider,pair,wise,connections,deal,struc,tured,In,many,real,world,between,objects,are,complex,go,beyond,flexible,modeling,tool,describe,higher,order,correlations,researchers,been,concerned,hypergraph,existing,show,better,performance,node,classification,tasks,so,while,they,shallow,because,over,smoothing,fitting,gradient,To,tackle,these,issues,present,novel,We,design,by,using,technologies,sampling,residual,identity,mapping,bring,from,convolutional,evaluate,visual,datasets,experiments,positive,effects
AB值：
0.513873
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
