融合全局和局部特征的胶囊图神经网络

doi:10.13229/j.cnki.jdxbgxb20200034

Abstract

Abstract:

The overall structure information is obtained in the training of the capsule graph neural network, and as the layers increases, the structure feature information of the node will be lost. A capsule graph neural network that combines global and local features was proposed. First， the Node2vec is improved， and the attribute information of nodes is introduced into the random walk process， so that the network structure and the attributes of nodes are taken into account when the network representation is generated. Then， the improved Node2vec is introduced into the capsule graph neural network， and the capsule graph neural network is designed which fuses global and local characteristics. Experimental results show that the proposed capsule graph neural network has faster training convergence， and higher graph classification accuracy.

Key words: computer application technology, network representation learning, complex network, graph neural network

CLC Number:

TP181

Rong QIAN,Ru ZHANG,Ke-jun ZHANG,Xin JIN,Shi-liang GE,Sheng JIANG. Capsule graph neural network based on global and local features fusion[J].Journal of Jilin University(Engineering and Technology Edition), 2021, 51(3): 1048-1054.

Figures/Tables 9

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Table 2

Table 3

Fig.6

References 18

1	Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
2	Bruna J, Zaremba W, Szlam A, et al. Spectral networks and locally connected networks on graphs[J/OL]. [2019-01-02].
3	Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering[C]∥Advances in Neural Information Processing Systems, San Francisco,2016:3844-3852.
4	Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J/OL]. [2020-01-04].
5	Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs[C]∥Proceedings of the 31st International Conference on Neural Information Processing, San Francisco, 2017:1025-1035.
6	Verma S, Zhang Z L. Graph capsule convolutional neural networks[J/OL]. [2020-01-02].
7	Mallea M D G, Meltzer P, Bentley P J. Capsule neural networks for graph classification using explicit tensorial graph representations[J/OL]. [2020-01-04].
8	Zhu Z, Peng G, Chen Y, et al. A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis[J]. Neurocomputing,2019,323: 62-75.
9	Grover A, Leskovec J. Node2vec: scalable feature learning for networks[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2016: 855-864.
10	Perozzi B, Al-Rfou R, Skiena S. Deepwalk: online learning of social representations[C]∥Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2014:701-710.
11	Ribeiro L F R, Saverese P H P, Figueiredo D R. Struc2vec: learning node representations from structural identity[C]∥Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2017:385-394.
12	Tang J, Qu M, Wang M, et al. LINE: large-scale information network embedding[C]∥Proceedings of the 24th International Conference on World Wide Web, Piscataway, 2015:1067-1077.
13	Henaff M, Bruna J, LeCun Y. Deep convolutional networks on graph-structured data[J/OL]. [2019-01-06].
14	Sabour S, Frosst N, Hinton G E. Dynamic routing between capsules[J/OL]. [2020-01-08].
15	Shervashidze N, Schweitzer P, van Leeuwen E J, et al. Weisfeiler-lehman graph kernels[J]. Journal of Machine Learning Research,2011,1(3):2539-2561.
16	Rezaee B. A cluster validity index for fuzzy clustering[J]. Fuzzy Sets and Systems, 2010, 161(23):3014-3025.
17	Wang H, Fan W, Yu P S, et al. Mining concept-drifting data streams using ensemble classifiers[C]∥Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2003:226-235.
18	Wang Y, Sun Y, Liu Z, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics,2019,38(5):1-12.

Related Articles 14

[1]	Qian-yi XU,Gui-he QIN,Ming-hui SUN,Cheng-xun MENG. Classification of drivers' head status based on improved ResNeSt [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(2): 704-711.
[2]	Xiao-hui WEI,Bing-yi SUN,Jia-xu CUI. Recommending activity to users via deep graph neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 278-284.
[3]	Yuan SONG,Dan-yuan ZHOU,Wen-chang SHI. Method to enhance security function of OpenStack Swift cloud storage system [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 314-322.
[4]	Xiang-jiu CHE,You-zheng DONG. Improved image recognition algorithm based on multi⁃scale information fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(5): 1747-1754.
[5]	MA Jian, FAN Jian-ping, LIU Feng, LI Hong-hui. The evolution model of objective-oriented software system [J]. 吉林大学学报(工学版), 2018, 48(2): 545-550.
[6]	SHI Xiao-hu, FENG Guo-xiang, LI Mu, LI Ying, WU Chun-guo. Overlapping community detection method based on density peaks [J]. 吉林大学学报(工学版), 2017, 47(1): 242-248.
[7]	HUANG Lan, LI Yu, WANG Gui-shen, WANG Yan. Community detection method based on vertex distance and clustering of density peaks [J]. 吉林大学学报(工学版), 2016, 46(6): 2042-2051.
[8]	GUO Yu-quan, LI Xiong-fei. Fractal clustering method for uncovering community of complex network [J]. 吉林大学学报(工学版), 2016, 46(5): 1633-1638.
[9]	HU Guan-yu, QIAO Pei-li. High dimensional differential evolutionary algorithm based on cloud population for network security prediction [J]. 吉林大学学报(工学版), 2016, 46(2): 568-577.
[10]	TONG Jin, WANG Ya-hui, FAN Xue-mei, ZHANG Shu-jun, CHEN Dong-hui. Monitoring system of cold chain logistics for farm fresh produce [J]. 吉林大学学报(工学版), 2013, 43(06): 1707-1711.
[11]	YE Yu-xin, ZHAO Jian-min, MO Yu-chang, OUYANG Dan-tong, LIU Hua-wen. CCA-based mining algorithm of modules in in complex networks [J]. 吉林大学学报(工学版), 2013, 43(02): 424-428.
[12]	LIU Da-you, YANG Jian-ning, YANG Bo, ZHAO Xue-hua, Jin Di. Community mining from complex networks based on loop tightness [J]. 吉林大学学报(工学版), 2013, 43(01): 98-105.
[13]	JIN Xin, XIE Bin, ZHU Jian-ming. Micro-blog network public opinion diffusion based on complex network analysis [J]. 吉林大学学报(工学版), 2012, 42(增刊1): 271-275.
[14]	LIU Da-you, ZHANG Dong-wei, LI Ni-ya, LIU Jie, JIN Di. Selective approach for neural network ensemble based on network clustering technology and its application [J]. 吉林大学学报(工学版), 2011, 41(4): 1034-1040.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

数据集	类	数据大小	标签	平均节点数	平均边个数
COLLAB	3	5000	无	74.49	4914.99
IMDB-B	2	1000	无	19.77	193.06
IMDB-M	3	1500	无	13	131.87
D&D	2	1178	有	284.31	715.65
ENZYMES	6	600	有	32.46	63.14

算法	COLLAB	IMDB-B	IMDB-M	D&D	ENZYMES
WL	79.02±1.77	73.40±4.63	49.33±4.75	79.78±0.36	52.22±1.26
GK	72.84±0.28	65.87±0.98	43.89±0.38	78.45±0.26	32.70±1.20
AWE	73.93±1.94	74.45±5.83	51.54±3.61	71.51±4.02	35.77±5.93
DGCNN	73.76±0.49	70.03±0.86	47.83±0.85	79.37±0.94	51.00±7.29
CapsGNN	79.62±0.91	73.10±4.83	50.27±2.65	75.38±4.17	54.67±5.67
GLCapsGNN	77.88±4.19	75.62±5.38	63.12±2.26	74.88±3.42	58.43±4.25

算法	COLLAB		IMDB-B		IMDB-M		D&D		ENZYMES
算法	时间/s	内存/%	时间/s	内存/%	时间/s	内存/%	时间/s	内存/%	时间/s	内存/%
CapsGNN	0.5463	63	0.1608	59	0.1574	57	6.1603	87	2.2738	71
GLCapsGNN	0.5792	61	0.1945	59	0.1753	58	6.6494	89	2.3452	72

Capsule graph neural network based on global and local features fusion

RICH HTML

PDF (PC)