基于粗糙图的图卷积神经网络算法

doi:10.16451/j.cnki.issn1003-6059.202209006

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1040 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract A topology graph is utilized to portray the relationship between nodes and node features are updated on the basis of the topology graph, when the graph convolutional neural network is applied for solving node classification problems. However, traditional topology graph can only portray definite relationships between nodes, i.e. fixed values of connected edge weights, ignoring the widespread uncertainty in the real world. The uncertainty affects not only the relationship between nodes, but also the final classification performance of the model. To overcome this defect, a graph convolutional neural network algorithm based on rough graphs is proposed. Firstly, the rough edges are constructed via the upper-lower approximation theory and the edge theory of traditional topology graph, and the uncertain relationships between nodes are inscribed in rough edges using maximum-minimum relationship values coming in pairs to construct a rough graph. Then, an end-to-end trainable neural network architecture based on rough graphs is designed, the rough graphs trained with rough weight coefficients are fed into the graph convolutional neural network, and the node features are updated based on the uncertain information. Finally, nodes are classified according to the learned node features. The experiments on real dataset show that the proposed algorithm improves the accuracy of node classification.

Key words： Graph Convolutional Neural Network Topology Graph Rough Set Rough Graph Uncertain Relationship

Received: 18 July 2022

ZTFLH:

TP 18

Fund:Supported by National Natural Science Foundation of China(No.61976120,62006128,62102199), Natural Science Foundation of Jiangsu Province(No.BK20191445), Jiangsu Innovation and Entrepreneurship program(No.(2020)30986), Key Project of Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.21KJA510004), General Project of Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.20KJB520009), Basic Science Research Program of Nantong Science and Technology Bureau(No.JC2020141, JC2021122), China Postdoctoral Science Foundation(No.2022M711716), Humanities and Social Science Fund of Ministry of Education of China(No.21YJCZH013)

Corresponding Authors: DING Weiping, Ph.D., professor. His research interests include data mining, machine learning, granular computing, evolutionary computing and big data analytics.

About author:: PAN Bairu, master student. Her research interests include data mining and deep lear-ning. JU Hengrong, Ph.D., associate professor. His research interests include granular computing, rough sets, machine learning and know-ledge discovery.HUANG Jiashuang, Ph.D., lecturer. His research interests include brain network analysis and deep learning.CHENG hun,Ph.D., lecturer. His research interests include social networks and multi-agent systems.SHEN Xinjie,master student. His research interests include data mining and deep lear-ning.GENG Yu,master student. His research interests include granular computing, machine learning and deep learning.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	PAN Bairu
	DING Weiping
	JU Hengrong
	HUANG Jiashuang
	CHENG Chun
	SHEN Xinjie
	GENG Yu

Cite this article:

PAN Bairu,DING Weiping,JU Hengrong等. Graph Convolutional Neural Network Algorithm Based on Rough Graphs[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(9): 827-838.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202209006 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I9/827

[1] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[2] YU B, YIN H T, ZHU Z X.Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting // Proc of the 27th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2018: 3634-3640.
[3] YING R, HE R N, CHEN K F, et al. Graph Convolutional Neural Networks for Web-Scale Recommender Systems // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 974-983.
[4] PARISOT S, KTENA S I, FERRANTE E, et al. Spectral Graph Convolutions for Population-Based Disease Prediction // Proc of the International Conference on Medical Image Computing and Compu-ter-Assisted Intervention. Berlin, Germany: Springer, 2017: 177-185.
[5] PARISOT S, KTENA S I, FERRANTE E, et al. Disease Prediction Using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease. Medical Image Analysis, 2018, 48: 117-130.
[6] KIPF T N, WELLING M.Semi-Supervised Classification with Graph Convolutional Networks[C/OL]. [2022-06-12].https://arxiv.org/pdf/1609.02907.pdf.
[7] ZACHARY W W.An Information Flow Model for Conflict and Fission in Small Groups. Journal of Anthropological Research, 1977, 33(4): 452-473.
[8] LIU X Y, TANG T, DING N.Social Network Sentiment Classification Method Combined Chinese Text Syntax with Graph Convolu-tional Neural Network. Egyptian Informatics Journal, 2022, 23(1): 1-12.
[9] ZADEH L A. Fuzzy Sets. Information and Control, 1965, 8(3): 338-353.
[10] ROSENFELD A.Fuzzy Graphs // ZADCH L A, FU K S, TANNKA K, eds. Fuzzy Sets and Their Applications to Cognitive and Decision Processes. New York, USA: Academic Press, 1975: 77-95.
[11] HUANG Y X, CHUNG A C S. Edge-Variational Graph Convolutional Networks for Uncertainty-Aware Disease Prediction // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2020: 562-572.
[12] YAO K X, LIANG J Y, LIANG J Q, et al. Multi-view Graph Convolutional Networks with Attention Mechanism. Artificial Intelligence, 2022, 307. DOI: 10.1016/j.artint.2022.103708.
[13] SEN P, NAMATA G, BILGIC M, et al. Collective Classification in Network Data. AI Magazine, 2008, 29(3): 93-106.
[14] CUI Z Y, HENRICKSON K, KE R M, et al. Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(11): 4883-4894.
[15] TONG T, GAO Q Q, GUERRERO R, et al. A Novel Grading Biomarker for the Prediction of Conversion from Mild Cognitive Impairment to Alzheimer's Disease. IEEE Transactions on Biomedical Engineering, 2016, 64(1): 155-165.
[16] WOLZ R, ALJABAR P, HAJNAL J V, et al. Nonlinear Dimensionality Reduction Combining MR Imaging with Non-imaging Information. Medical Image Analysis, 2012, 16(4): 819-830.
[17] BROSCH T, TAM R.Manifold Learning of Brain MRIs by Deep Learning // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2013: 633-640.
[18] PARISOT S, DARLIX A, BAUMANN C, et al. A Probabilistic Atlas of Diffuse WHO Grade II Glioma Locations in the Brain. PLoS One, 2016, 11(1). DOI: 10.1371/journal.pone.0144200.
[19] WANG Z X, ZHU X F, ADELI E, et al. Multi-modal Classification of Neurodegenerative Disease by Progressive Graph-Based Transductive Learning. Medical Image Analysis, 2017, 39: 218-230.
[20] PAWLAK Z. Rough Sets. International Journal of Computer and Information Sciences, 1982, 11(5): 341-356.
[21] LI R Y, WANG S, ZHU F Y, et al. Adaptive Graph Convolutional Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 3546-3553.
[22] 王国胤,姚一豫,于洪.粗糙集理论与应用研究综述.计算机学报, 2009, 32(7): 1229-1246.
(WANG G Y, YAO Y Y, YU H.A Survey on Rough Set Theory and Applications. Chinese Journal of Computers, 2009, 32(7): 1229-1246.)
[23] ZHANG S, TONG H H, XU J J, et al. Graph Convolutional Networks: A Comprehensive Review. Computational Social Networks, 2019, 6(1). DOI: 10.1186/s40649-019-0069-y.
[24] WERLING D M, GESCHWIND D H.Sex Differences in Autism Spectrum Disorders. Current Opinion in Neurology, 2013, 26(2): 146-153.
[25] MOHAMMAD-REZAZADEH I, FROHLICH J, LOO S K, et al. Brain Connectivity in Autism Spectrum Disorder. Current Opinion in Neurology, 2016, 29(2): 137-147.
[26] ABRAHAM A, MILHAM M P, DI MARTINO A, et al. Deriving Reproducible Biomarkers from Multi-site Resting-State Data: An Autism-Based Example. NeuroImage, 2017, 147: 736-745.
[27] MARQUARDT D W, SNEE R D.Ridge Regression in Practice. The American Statistician, 1975, 29(1): 3-20.
[28] SCARSELLI F, GORI M, TSOI A C, et al. The Graph Neural Net-work Model. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[29] VELI ČKOVI Ć P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[C/OL].[2022-06-12]. https://arxiv.org/pdf/1710.10903.pdf.
[30] WEI D T, ZHUANG K X, AI L, et al. Structural and Functional Brain Scans from the Cross-Sectional Southwest University Adult Lifespan Dataset. Scientific Data, 2018, 5(1). DOI: 10.1038/sdata.2018.134.