DeepHGNN:A Novel Deep Hypergraph Neural Network

查看全文 作　　者：LIN [1,2,3,4]Jingjing;YE [1,2,3]Zhonglin;ZHAO [1,2,3]Haixing;FANG [2,3]Lusheng

机构地区：[1]College of Computer,Qinghai Normal University,Xining 810008,China;[2]The State Key Laboratory of Tibetan Intelligent Information Processing and Application,Xining 810008,China;[3]Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province,Xining 810008,China;[4]Xining Urban Vocational&Technical College,Xining 810003,China

出　　处：《Chinese Journal of Electronics》索引2022年第31卷第5期,共11页

基　　金：supported by the National Key R&D Program of China(2020YFC1523300);the Youth Program of Natural Science Foundation of Qinghai Province (2021-ZJ-946Q);the Middle-Youth Program of Natural Science Foundation of Qinghai Normal University (2020QZR007) 摘　　要：With the development of deep learning,graph neural networks(GNNs)have yielded substantial results in various application fields.GNNs mainly consider the pair-wise connections and deal with graph-structured 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 intricate 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 oversmoothing,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 classification tasks. 关键词：Deep neural networks Graph neural network Hypergraph neural network Deep hypergraph neural network

相关文献

参考文献（47）
引证文献（2）
耦合文献（345）

参考文献(47)

引证文献(2)

耦合文献(345)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

DeepHGNN:A Novel Deep Hypergraph Neural Network

参考文献(47)

引证文献(2)

耦合文献(345)

用户提示