Graph convolutional network method based on hybrid feature modeling

doi:10.11772/j.issn.1001-9081.2021111981

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (11): 3354-3363.DOI: 10.11772/j.issn.1001-9081.2021111981

• CCF Bigdata 2021 • Previous Articles

Graph convolutional network method based on hybrid feature modeling

Zhuoran LI¹^,²^,³^,⁴, Zhonglin YE¹^,²^,³^,⁴, Haixing ZHAO¹^,²^,³^,⁴(), Jingjing LIN¹^,²^,³^,⁴

^1.Computer College，Qinghai Normal University，Xining Qinghai 810016，China
^2.State Key Laboratory of Tibetan Intelligent Information Processing and Application Co?established by Ministry of Science and Technology and Qinghai Province （Qinghai Normal University），Xining Qinghai 810008，China
^3.Key Laboratory of Tibetan Information Processing，Ministry of Education （Qinghai Normal University），Xining Qinghai 810008，China
^4.Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province （Qinghai Normal University），Xining Qinghai 810008，China

Received:2021-11-22 Revised:2022-01-12 Accepted:2022-01-14 Online:2022-01-25 Published:2022-11-10
Contact: Haixing ZHAO
About author:LI Zhuoran， born in 1996， M. S. candidate. His research interests include data mining， graph neural network.
YE Zhongli， born in 1989， Ph. D.， associate professor. His research interests include question answering system， network representation learning.
ZHAO Haixing， born in 1969， Ph. D.， professor. His research interests include complex network， network reliability.
LIN Jingjing， born in 1986， Ph. D. candidate， lecturer. Her research interests include data mining， hypergraph neural network.
Supported by:
National Key Research and Development Program of China(2020YFC1523300);Natural Science Foundation of Qinghai Province(2021?ZJ?946Q);Middle?Youth Natural Science Foundation of Qinghai Normal University(2020QZR007)

基于混合特征建模的图卷积网络方法

李卓然¹^,²^,³^,⁴, 冶忠林¹^,²^,³^,⁴, 赵海兴¹^,²^,³^,⁴(), 林晶晶¹^,²^,³^,⁴

^1.青海师范大学计算机学院, 西宁 810016
^2.省部共建藏语智能信息处理及应用国家重点实验室(青海师范大学), 西宁 810008
^3.藏文信息处理教育部重点实验室(青海师范大学), 西宁 810008
^4.青海省藏文信息处理与机器翻译重点实验室(青海师范大学), 西宁 810008

通讯作者: 赵海兴
作者简介:李卓然（1996—），男，内蒙古乌兰察布人，硕士研究生，CCF会员，主要研究方向：数据挖掘、图神经网络
冶忠林（1989—），男，青海民和人，副教授，博士，CCF会员，主要研究方向：问答系统、网络表示学习
赵海兴（1969—），男，青海湟中人，教授，博士，CCF会员，主要研究方向：复杂网络、网络可靠性 h.x.zhao@163.com
林晶晶（1986—），女，甘肃临洮人，讲师，博士研究生，CCF会员，主要研究方向：数据挖掘、超图神经网络。
基金资助:
国家重点研发计划项目(2020YFC1523300);青海省自然科学基金资助项目(2021?ZJ?946Q);青海师范大学自然科学中青年科研基金资助项目(2020QZR007)

Abstract

Abstract:

For the complex information contained in the network， more ways are needed to extract useful information from it， but the relevant characteristics in the network cannot be completely described by the existing single?feature Graph Neural Network （GNN）. To resolve the above problems， a Hybrid feature?based Dual Graph Convolutional Network （HDGCN） was proposed. Firstly， the structure feature vectors and semantic feature vectors of nodes were obtained by Graph Convolutional Network （GCN）. Secondly， the features of nodes were aggregated selectively so that the feature expression ability of nodes was enhanced by the aggregation function based on attention mechanism or gating mechanism. Finally， the hybrid feature vectors of nodes were gained by the fusion mechanism based on a feasible dual?channel GCN， and the structure features and semantic features of nodes were modeled jointly to make the features be supplement for each other and promote the method's performance on subsequent machine learning tasks. Verification was performed on the datasets CiteSeer， DBLP （DataBase systems and Logic Programming） and SDBLP （Simplified DataBase systems and Logic Programming）. Experimental results show that compared with the graph convolutional network model based on structure feature training， the dual channel graph convolutional network model based on hybrid feature training has the average value of Micro?F1 increased by 2.43， 2.14， 1.86 and 2.13 percentage points respectively， and the average value of Macro?F1 increased by 1.38， 0.33， 1.06 and 0.86 percentage points respectively when the training set proportion is 20%， 40%， 60% and 80%. The difference in accuracy is no more than 0.5 percentage points when using concat or mean as the fusion strategy， which shows that both concat and mean can be used as the fusion strategy. HDGCN has higher accuracy on node classification and clustering tasks than models trained by structure or semantic network alone， and has the best results when the output dimension is 64， the learning rate is 0.001， the graph convolutional layer number is 2 and the attention vector dimension is 128.

Key words: attention mechanism, gating mechanism, dual channel graph convolutional network, structure feature, semantic feature

摘要：

对于网络中拥有的复杂信息，需要更多的方式抽取其中的有用信息，但现有的单特征图神经网络（GNN）无法完整地刻画网络中的相关特性。针对该问题，提出基于混合特征的图卷积网络（HDGCN）方法。首先，通过图卷积网络（GCN）得到节点的结构特征向量和语义特征向量；然后，通过改进基于注意力机制或门控机制的聚合函数选择性地聚合语义网络节点的特征，增强节点的特征表达能力；最后，通过一种基于双通道图卷积网络的融合机制得到节点的混合特征向量，将节点的结构特征和语义特征联合建模，使特征之间互相补充，提升该方法在后续各种机器学习任务上的表现。在CiteSeer、DBLP和SDBLP三个数据集上进行实验的结果表明，与基于结构特征训练的GCN相比，HDGCN在训练集比例为20%、40%、60%、80%时的Micro?F1值平均分别提升了2.43、2.14、1.86和2.13个百分点，Macro?F1值平均分别提升了1.38、0.33、1.06和0.86个百分点。用拼接或平均值作为融合策略时，准确率相差不超过0.5个百分点，可见拼接和平均值均可作为融合策略。HDGCN在节点分类和聚类任务上的准确率高于单纯使用结构或语义网络训练的模型，并且在输出维度为64、学习率为0.001、2层图卷积层和128维注意力向量时的效果最好。

关键词: 注意力机制, 门控机制, 双通道图卷积网络, 结构特征, 语义特征

CLC Number:

TP391

Zhuoran LI, Zhonglin YE, Haixing ZHAO, Jingjing LIN. Graph convolutional network method based on hybrid feature modeling[J]. Journal of Computer Applications, 2022, 42(11): 3354-3363.

李卓然, 冶忠林, 赵海兴, 林晶晶. 基于混合特征建模的图卷积网络方法[J]. 《计算机应用》唯一官方网站, 2022, 42(11): 3354-3363.

Figures/Tables 13

References 42

1	LIU Y， LIU S P， WANG Z F. A general framework for image fusion based on multi‑scale transform and sparse representation［J］. Information Fusion， 2015， 24： 147-164. 10.1016/j.inffus.2014.09.004
2	EASLEY G， LABATE D， LIM W Q. Sparse directional image representations using the discrete shearlet transform［J］. Applied and Computational Harmonic Analysis， 2008， 25（1）：25-46. 10.1016/j.acha.2007.09.003
3	KALCHBRENNER N， GREFENSTETTE E， BLUNSOM P. A convolutional neural network for modelling sentences［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2014： 655-665. 10.3115/v1/p14-1062
4	LE Q， MIKOLOV T. Distributed representations of sentences and documents［C］// Proceedings of the 31st International Conference on Machine Learning. New York： JMLR.org， 2014：1188-1196.
5	ZHAO M H， ZHONG S S， FU X Y， et al. Deep residual shrinkage networks for fault diagnosis［J］. IEEE Transactions on Industrial Informatics， 2020， 16（7）： 4681-4690. 10.1109/tii.2019.2943898
6	李涛，段礼祥，张东宁，等. 自适应卷积神经网络在旋转机械故障诊断中的应用［J］. 振动与冲击， 2020， 39（16）：275-282， 288. 10.13465/j.cnki.jvs.2020.16.037
	LI T， DUAN L X， ZHANG D N， et al. Application of adaptive convolutional neural network in rotating machinery fault diagnosis［J］. Journal of Vibration and Shock， 2020， 39（16）：275-282， 288. 10.13465/j.cnki.jvs.2020.16.037
7	KICK E L， McKINNEY L A， McDONALD S， et al. A multiple‑ network analysis of the world system of nations， 1995-1999［M］// SCOTT J， CARRINGTON P J. The SAGE Handbook of Social Network Analysis. Thousand Oaks， CA： SAGE Publications Ltd， 2014：311-328. 10.4135/9781446294413.n22
8	LIAO L Z， HE X N， ZHANG H W， et al. Attributed social network embedding［J］. IEEE Transactions on Knowledge and Data Engineering， 2018， 30（12）：2257-2270. 10.1109/tkde.2018.2819980
9	GLIGORIJEVIĆ V， BAROT M， BONNEAU R. deepNF： deep network fusion for protein function prediction［J］. Bioinformatics， 2018， 34（22）：3873-3881. 10.1093/bioinformatics/bty440
10	SU C， TONG J， ZHU Y J， et al. Network embedding in biomedical data science［J］. Briefings in Bioinformatics， 2020， 21（1）：182-197. 10.1093/bib/bby117
11	杨力川. 基于深度学习的交通标志识别研究综述［J］. 现代计算机， 2021（15）：3-5， 11. 10.3969/j.issn.1007-1423.2021.15.001
	YANG L C. Summary of research on traffic sign recognition based on deep learning［J］. Modern Computer， 2021（15）：3-5， 11. 10.3969/j.issn.1007-1423.2021.15.001
12	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［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 21（11）： 4883-4894. 10.1109/tits.2019.2950416
13	BRUNA J， ZAREMBA W， SZLAM A， et al. Spectral networks and locally connected networks on graphs［EB/OL］. （2014-04-21）［2021-11-26］..
14	DEFFERRARD M， BRESSON X， VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2016：3844-3852.
15	HAMMOND D K， VANDERGHEYNST P， GRIBONVAL R. Wavelets on graphs via spectral graph theory［J］. Applied and Computational Harmonic Analysis， 2011， 30（2）：129-150. 10.1016/j.acha.2010.04.005
16	KIPF T N， WELLING M. Semi‑supervised classification with graph convolutional networks［EB/OL］. （2017-02-22）［2021-11-26］. .
17	YANG C， LIU Z Y， ZHAO D L， et al. Network representation learning with rich text information［C］// Proceedings of the 24th International Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2015：2111-2117. 10.1609/aaai.v29i1.9448
18	冶忠林，赵海兴，张科，等. 基于多源信息融合的分布式词表示学习［J］. 中文信息学报， 2019， 33（10）：18-30. 10.3969/j.issn.1003-0077.2019.10.003
	YE Z L， ZHAO H X， ZHANG K， et al. Distributed word embedding via multi‑source information fusion［J］. Journal of Chinese Information Processing， 2019， 33（10）：18-30. 10.3969/j.issn.1003-0077.2019.10.003
19	YE Z L， ZHAO H X， ZHANG K， et al. Tri‑party deep network representation learning using inductive matrix completion［J］. Journal of Central South University， 2019， 26（10）： 2746-2758. 10.1007/s11771-019-4210-8
20	YE Z L， ZHAO H X， ZHU Y， et al. HSNR： a network representation learning algorithm using hierarchical structure embedding［J］. Chinese Journal of Electronics， 2020， 29（6）：1141-1152. 10.1049/cje.2020.10.001
21	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： ACM， 2014：701-710. 10.1145/2623330.2623732
22	TANG J， QU M， WANG M Z， et al. LINE： large‑scale information network embedding［C］// Proceedings of the 24th International Conference on World Wide Web. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2015： 1067-1077. 10.1145/2736277.2741093
23	WANG D X， CUI P， ZHU W W. Structural deep network embedding［C］// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2016： 1225-1234. 10.1145/2939672.2939753
24	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： ACM， 2016： 855-864. 10.1145/2939672.2939754
25	LI R Y， WANG S， ZHU F Y， et al. Adaptive graph convolutional neural networks［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2018：3546-3553. 10.1609/aaai.v32i1.11691
26	ZHUANG C Y， MA Q. Dual graph convolutional networks for graph‑based semi‑supervised classification［C］// Proceedings of the 2018 World Wide Web Conference. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2018： 499-508. 10.1145/3178876.3186116
27	XU B B， SHEN H W， CAO Q， et al. Graph wavelet neural network［EB/OL］. （2019-04-12）［2021-11-26］..
28	SCARSELLI F， GORI M， TSOI A C， et al. The graph neural network model［J］. IEEE Transactions on Neural Networks， 2009， 20（1）： 61-80. 10.1109/tnn.2008.2005605
29	LI Y J， ZEMEL R， BROCKSCHMIDT M， et al. Gated graph sequence neural networks［EB/OL］. （2017-09-22）［2021-11-26］..
30	ATWOOD J， TOWSLEY D. Diffusion‑convolutional neural networks［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2016：2001-2009.
31	HAMILTON W L， YING R， LESKOVEC J. Inductive representation learning on large graphs［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017：1025-1035. 10.7551/mitpress/11474.003.0014
32	GILMER J， SCHOENHOLZ S S， RILEY P F， et al. Neural message passing for quantum chemistry［C］// Proceedings of the 34th International Conference on Machine Learning. New York： JMLR.org， 2017：1263-1272.
33	MONTI F， BOSCAINI D， MASCI J， et al. Geometric deep learning on graphs and manifolds using mixture model CNNs［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017：5425-5434. 10.1109/cvpr.2017.576
34	WANG X L， GIRSHICK R， GUPTA A， et al. Non‑local neural networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018：7794-7803. 10.1109/cvpr.2018.00813
35	BATTAGLIA P W， HAMRICK J B， BAPST V， et al. Relational inductive biases， deep learning， and graph networks［EB/OL］. （2018-10-17）［2021-11-26］..
36	VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph attention networks［EB/OL］. （2018-02-04）［2021-11-26］..
37	ZHANG J N， SHI X J， XIE J Y， et al. GaAN： gated attention networks for learning on large and spatiotemporal graphs［C］// Proceedings of the Thirty‑Fourth Conference on Uncertainty in Artificial Intelligence. Arlington， VA： AUAI Press， 2018： No.139.
38	CHUNG J， GULCEHRE C， CHO K， et al. Empirical evaluation of gated recurrent neural networks on sequence modeling［EB/OL］. （2014-12-11）［2021-11-26］.. 10.1007/978-3-030-89929-5_3
39	LIANG X D， SHEN X H， FENG J S， et al. Semantic object parsing with Graph LSTM［C］// Proceedings of the 2016 European Conference on Computer Vision， LNCS 9905. Cham： Springer， 2016：125-143.
40	ZHANG Y， LIU Q， SONG L F. Sentence‑state LSTM for text representation［C］// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2018：317-327. 10.18653/v1/p18-1030
41	HOCHREITER S， SCHMIDHUBER J. Long short‑term memory［J］. Neural Computation， 1997， 9（8）：1735-1780. 10.1162/neco.1997.9.8.1735
42	LI X H， WEN L J， QIAN C， et al. GAHNE： graph‑aggregated heterogeneous network embedding［C］// Proceedings of the IEEE 32nd International Conference on Tools with Artificial Intelligence. Piscataway： IEEE， 2020：1012-1019. 10.1109/ictai50040.2020.00157

数据集	节点数	边数		样本数量
数据集	节点数	边数		训练集	验证集	测试集
CiteSeer	4 610	结构网络	5 923	1 333	667	2 610
CiteSeer	4 610	语义网络	819 346	1 333	667	2 610
DBLP	17 725	结构网络	105 781	3 333	1 667	12 725
DBLP	17 725	语义网络	125 360	3 333	1 667	12 725
SDBLP	3 119	结构网络	39 516	666	334	3 119
SDBLP	3 119	语义网络	439 182	666	334	3 119

数据集	节点数	边数		样本数量
数据集	节点数	边数		训练集	验证集	测试集
CiteSeer	4 610	结构网络	5 923	1 333	667	2 610
CiteSeer	4 610	语义网络	819 346	1 333	667	2 610
DBLP	17 725	结构网络	105 781	3 333	1 667	12 725
DBLP	17 725	语义网络	125 360	3 333	1 667	12 725
SDBLP	3 119	结构网络	39 516	666	334	3 119
SDBLP	3 119	语义网络	439 182	666	334	3 119

数据集	对比算法	训练集比例
数据集	对比算法	20%	40%	60%	80%
CiteSeer	DeepWalk	59.30	61.48	62.30	62.33
	LINE	47.06	49.57	51.02	53.07
	TF	61.30	63.05	63.30	62.19
	DeepWalk+TF	61.15	63.37	63.96	65.49
	GraRep	53.09	59.75	61.05	62.09
	HDGCN	83.52	84.26	83.95	85.15
DBLP	DeepWalk	64.34	65.98	66.18	67.03
	LINE	66.53	67.87	68.30	68.89
	TF	69.46	71.15	71.44	71.57
	DeepWalk+TF	65.15	66.22	66.60	66.91
	GraRep	65.90	67.92	68.88	69.56
	HDGCN	80.47	80.58	80.74	80.93
SDBLP	DeepWalk	80.65	81.49	82.35	82.71
	LINE	77.01	78.28	78.97	78.82
	TF	71.23	73.86	75.07	76.00
	DeepWalk+TF	80.95	81.44	82.22	82.58
	GraRep	82.52	84.78	84.17	85.27
	HDGCN	82.45	82.61	83.23	83.47

数据集	对比算法	训练集比例
数据集	对比算法	20%	40%	60%	80%
CiteSeer	DeepWalk	59.30	61.48	62.30	62.33
	LINE	47.06	49.57	51.02	53.07
	TF	61.30	63.05	63.30	62.19
	DeepWalk+TF	61.15	63.37	63.96	65.49
	GraRep	53.09	59.75	61.05	62.09
	HDGCN	83.52	84.26	83.95	85.15
DBLP	DeepWalk	64.34	65.98	66.18	67.03
	LINE	66.53	67.87	68.30	68.89
	TF	69.46	71.15	71.44	71.57
	DeepWalk+TF	65.15	66.22	66.60	66.91
	GraRep	65.90	67.92	68.88	69.56
	HDGCN	80.47	80.58	80.74	80.93
SDBLP	DeepWalk	80.65	81.49	82.35	82.71
	LINE	77.01	78.28	78.97	78.82
	TF	71.23	73.86	75.07	76.00
	DeepWalk+TF	80.95	81.44	82.22	82.58
	GraRep	82.52	84.78	84.17	85.27
	HDGCN	82.45	82.61	83.23	83.47

数据集	特征类型	训练集比例
		20%		40%		60%		80%
		Micro‑F1	Macro‑F1	Micro‑F1	Macro‑F1	Micro‑F1	Macro‑F1	Micro‑F1	Macro‑F1
CiteSeer	Hybrid	83.52	54.13	84.26	57.23	83.95	62.46	85.15	64.11
	Structure	77.58	52.38	78.75	58.08	80.26	62.32	80.69	64.36
	Semantic	65.19	44.07	65.76	44.40	66.93	45.08	67.18	47.05
SDBLP	Hybrid	82.45	82.45	82.61	82.63	83.23	83.23	83.47	83.42
	Structure	81.46	81.15	82.11	81.82	81.56	81.15	82.17	81.90
	Semantic	65.80	64.45	66.00	65.77	66.89	66.62	68.44	68.03
DBLP	Hybrid	80.47	74.45	80.58	74.70	80.74	74.85	80.93	74.99
	Structure	80.10	73.36	80.18	73.66	80.51	73.90	80.29	73.67
	Semantic	64.73	50.10	65.52	52.06	66.11	53.27	66.71	54.28

Graph convolutional network method based on hybrid feature modeling

基于混合特征建模的图卷积网络方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 42

Related Articles 15

Recommended Articles

Metrics

数据集	特征类型	NMI	ARI
CiteSeer	结构特征	58.90	37.17
	语义特征	33.84	22.06
	混合特征	59.18	37.12
SDBLP	结构特征	55.93	56.03
	语义特征	29.51	23.94
	混合特征	56.47	56.48
DBLP	结构特征	43.41	47.30
	语义特征	22.68	20.90
	混合特征	43.33	45.05

数据集	融合方式	训练集比例
数据集	融合方式	20%	40%	60%	80%
CiteSeer	sum	83.72	84.56	84.67	85.38
	mean	84.18	85.32	85.56	85.57
	concat	83.52	84.26	83.95	85.15
SDBLP	sum	81.93	82.25	81.92	81.93
	mean	83.41	83.55	83.56	83.49
	concat	82.45	82.61	83.23	83.47
DBLP	Sum	80.07	79.97	79.88	80.11
	mean	79.85	79.81	79.66	80.04
	concat	80.47	80.58	80.74	80.93

[1]	Yaoshun LI, Lizhi LIU. Lightweight network for rebar detection with attention mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2900-2908.
[2]	Hongjun HENG, Tianbao XU. Attention sentiment analysis model based on multi-scale convolution and gating mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2674-2679.
[3]	Xudong HOU, Fei TENG, Yi ZHANG. Medical named entity recognition model based on deep auto-encoding [J]. Journal of Computer Applications, 2022, 42(9): 2686-2692.
[4]	Yuefeng LIU, Xiaoyan ZHANG, Wei GUO, Haodong BIAN, Yingjie HE. Remaining useful life prediction method of aero-engine based on optimized hybrid model [J]. Journal of Computer Applications, 2022, 42(9): 2960-2968.
[5]	Kai WEN, Weiwei TANG, Junchen XIONG. Real-time segmentation algorithm based on attention mechanism and effective factorized convolution [J]. Journal of Computer Applications, 2022, 42(9): 2659-2666.
[6]	Haiyun WEI, Qianying ZHENG, Jinling YU. Motion blurred image restoration algorithm based on multi-scale network [J]. Journal of Computer Applications, 2022, 42(9): 2838-2844.
[7]	Wentao ZHANG, Yuanyu WANG, Saize LI. Depth estimation model of single haze image based on conditional generative adversarial network [J]. Journal of Computer Applications, 2022, 42(9): 2865-2875.
[8]	Kun LI, Qing HOU. Lightweight human pose estimation based on attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2407-2414.
[9]	Liying ZHANG, Chunjiang PANG, Xinying WANG, Guoliang LI. Multi-scale object detection algorithm based on improved YOLOv3 [J]. Journal of Computer Applications, 2022, 42(8): 2423-2431.
[10]	Xinyu ZHANG, Sheng DING, Zhipei YANG. Traffic sign detection algorithm based on improved attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2378-2385.
[11]	Yinglü XUAN, Yuan WAN, Jiahui CHEN. Time series classification by LSTM based on multi-scale convolution and attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2343-2352.
[12]	Minghui WU, Guangjie ZHANG, Canghong JIN. Time series prediction model based on multimodal information fusion [J]. Journal of Computer Applications, 2022, 42(8): 2326-2332.
[13]	Zhenhu LYU, Xinzheng XU, Fangyan ZHANG. Lightweight attention mechanism module based on squeeze and excitation [J]. Journal of Computer Applications, 2022, 42(8): 2353-2360.
[14]	Chengxia XU, Qing YAN, Teng LI, Kaichao MIAO. De-raining algorithm based on joint attention mechanism for single image [J]. Journal of Computer Applications, 2022, 42(8): 2578-2585.
[15]	Zefang HAN, Xiong ZHANG, Hong SHANGGUAN, Xinglong HAN, Jing HAN, Gang FENG, Xueying CUI. Artifacts sensing generative adversarial network for low-dose CT denoising [J]. Journal of Computer Applications, 2022, 42(7): 2301-2310.