Computer Science ›› 2022, Vol. 49 ›› Issue (3): 129-133.doi: 10.11896/jsjkx.201100152

• Database & Big Data & Data Science • Previous Articles     Next Articles

Multi-site Hyper-graph Convolutional Neural Networks and Application

ZHOU Hai-yu, ZHANG Dao-qiang   

  1. 1 College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
    2 MIIT Key Laboratory of Pattern Analysis and Machine Intelligence,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
  • Received:2020-11-23 Revised:2021-12-08 Online:2022-03-15 Published:2022-03-15
  • About author:ZHOU Hai-yu,born in 1994,postgra-duate.His main research interests include computer vision and medical image analysis.
    ZHANG Dao-qiang,born in 1978,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include machine lear-ning,pattern recognition,data mining and medical image analysis.
  • Supported by:
    National Natural Science Foundation of China(61876082,61861130366,61732006)

Abstract: Recently,the exploitation of graph neural networks for neurological brain disorder diagnosis has attracted much attention.However,the graphs used in the existing studies are usually based on the pairwise connections of different nodes,and thus cannot reflect the complex correlation of three or more subjects,especially in the multi-site dataset,i.e.,the dataset collected from different medical institutions with the problem of data heterogeneity resulted from various scanning parameters or subject population.To address this issue,a multi-site hypergraph data structure is proposed to describe the relationship between multi-site data.This hypergraph consists of two types hyper-edge,one is intra-site hyper-edge that describes the relationship within the site,and the other is inter-site hyper-edge that describes relationship between different sites.Also,a hypergraph convolutional network is proposed to learn the feature representation of each node.The hypergraph convolution consists of two parts:the first part is the hypergraph node convolution,the second part is the super edge convolution.Experimental results on two multi-site datasets can also validate the effectiveness of the proposed method.

Key words: Brain diseases diagnosis, Data heterogeneity, Graph convolutional networks, Hyper-graph convolutional networks, Multi-site dataset

CLC Number: 

  • TP181
[1]SCARSELLI F,GORI M,TSOI A C,et al.The Graph NeuralNetwork Model[J].IEEE Transactions on Neural Networks,2009,20(1):61-80.
[2]BRUNA J,ZAREMBA W,SZLAM A.Yann LeCun:SpectralNetworks and Locally Connected Networks on Graphs[C]//International Conference on Learning Representations.2014.
[3]DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering [C]//Advances in Neural Information Processing Systems.2016:3844-3852.
[4]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[C]//International Conference on Learning Representations.2017.
[5]ATWOOD J,TOWSLEY D.Diffusion convolutional neural networks[C]//Advances in Neural Information Processing Systems.2016:1993-2001.
[6]DUVENAUD D K,MACLAURIN D,IPARRAGUIRRE J,et al.Convolutional networks on graphs for learning molecular fingerprints [C]//Advances in Neural Information Processing Systems.2015:2224-2232.
[7]HAMILTON W,YING Z T,LESKOVEC J.Inductive representation learning on large graphs [C]//Advances in Neural Information Processing Systems.2017:1024-1034.
[8]KTENA S I,PARISOT S,FERRANTE E,et al.Distance metric learning using graph convolutional networks:Application to functional brain networks [C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer,2017:469-477.
[9]PARISOT S,KTENA S I,FERRANTE E,et al.Disease predic-tion using graph convolutional networks:application to autism spectrum disorder and Alzheimer’s disease[J].Medical Image Analysis,2018,48:117-130.
[10]HUANG Y C,LIU Q S,METAXAS D.Video object segmentation by hypergraph cut [C]//IEEE Conference on Computer Vision and Pattern Recognition.2009:1738-1745.
[11]ZHANG Z Z,LIN H J,GAO Y,et al.Dynamic HypergraphStructure Learning [C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence.2018:3162-3169.
[12]FENG Y F,YOU H X,ZHANG Z Z,et al.Hypergraph neural networks [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:3558-3565.
[13]BAI S,ZHANG F H,TORR P H S.Hypergraph convolutionand hypergraph attention[J].arXiv:1901.08150,2019.
[14]JIANG J W,WEI Y X,FENG Y F,et al.Dynamic hypergraph neural networks[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.2019:2635-2641.
[15]MARTINO A D,YAN C G,LI Q,et al.The autism brain ima-ging data exchange:towards a large-scale evaluation of the intrinsic brain architecture in autism[J].Molecular Psychiatry,2014,19(6):659-667.
[16]MAO B C,HUANG J S,ZHANG D Q.Node based row filter convolutional neural network for brain network classification [C]//Pacific Rim International Conference on Artificial Intelligence.2018:1069-1080.
[17]KTENA S I,PARISOT S,FERRANTE E,et al.Metric learning with spectral graph convolutions on brain connectivity networks[J].NeuroImage,2018,169:431-442.
[1] PAN Zhi-hao, ZENG Bi, LIAO Wen-xiong, WEI Peng-fei, WEN Song. Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification [J]. Computer Science, 2022, 49(3): 294-300.
[2] JIANG Zong-li, LI Miao-miao, ZHANG Jin-li. Graph Convolution of Fusion Meta-path Based Heterogeneous Network Representation Learning [J]. Computer Science, 2020, 47(7): 231-235.
Full text



No Suggested Reading articles found!