图网络层级信息挖掘分类算法综述

魏文超; 蔺广逢; 廖开阳; 康晓兵; 赵凡

doi:10.11834/jig.210267

综述 | 浏览量 : 0 下载量: 1725 CSCD: 0

PDF
导出
分享
收藏
专辑

图网络层级信息挖掘分类算法综述
Survey of graph network hierarchical information mining for classification
2022年27卷第10期页码：2916-2936
收稿：2021-04-16，

修回：2021-7-7，

录用：2021-7-15，

纸质出版：2022-10-16
DOI： 10.11834/jig.210267
稿件说明：

移动端阅览

魏文超, 蔺广逢, 廖开阳, 康晓兵, 赵凡. 图网络层级信息挖掘分类算法综述[J]. 中国图象图形学报, 2022,27(10):2916-2936. DOI： 10.11834/jig.210267.

Wenchao Wei, Guangfeng Lin, Kaiyang Liao, Xiaobing Kang, Fan Zhao. Survey of graph network hierarchical information mining for classification[J]. Journal of Image and Graphics, 2022, 27(10): 2916-2936. DOI： 10.11834/jig.210267.

摘要

深度学习作为人工智能的一个研究分支发展迅速，而研究数据主要是语音、图像和视频等，这些具有规则结构的数据通常在欧氏空间中表示。然而许多学习任务需要处理的数据是从非欧氏空间中生成，这些数据特征和其关系结构可以用图来定义。图卷积神经网络通过将卷积定理应用于图，完成节点之间的信息传播与聚合，成为建模图数据一种有效的方法。尽管图卷积神经网络取得了巨大成功，但针对图任务中的节点分类问题，由于深层图结构优化的特有难点——过平滑现象，现有的多数模型都只有两三层的浅层模型架构。在理论上，图卷积神经网络的深层结构可以获得更多节点表征信息，因此针对其层级信息进行研究，将层级结构算法迁移到图数据分析的核心在于图层级卷积算子构建和图层级间信息融合。本文对图网络层级信息挖掘算法进行综述，介绍图神经网络的发展背景、存在问题以及图卷积神经网络层级结构算法的发展，根据不同图卷积层级信息处理将现有算法分为正则化方法和架构调整方法。正则化方法通过重新构建图卷积算子更好地聚合邻域信息，而架构调整方法则融合层级信息丰富节点表征。图卷积神经网络层级特性实验表明，图结构中存在层级特性节点，现有图层级信息挖掘算法仍未对层级特性节点的图信息进行完全探索。最后，总结了图卷积神经网络层级信息挖掘模型的主要应用领域，并从计算效率、大规模数据、动态图和应用场景等方面提出进一步研究的方向。

Abstract

Deep learning based data format is mainly related to voice

image and video. A regular data structure is usually represented in Euclidean space. The graph structure representation of non-Euclidean data can be used more widely in practice. A typical data structure graphs can describe the features of objects and the relationship between objects simultaneously. Therefore

the application research of graphs in deep learning has been focused on as a future research direction. However

learning data are generated from non-Euclidean spaces in common

and these data features and their relational structure can be defined by graphs. The graph neural network is facilitated to extend the neural network via process data processing in the graph domain. Each node is clarified by updating the expression of the node related to the neighbor node and the edge structure

which designates a research framework for subsequent research. With the help of the graph neural network framework

the graph convolutional neural network defines the updating functions on the convolutional aspect

information dissemination and aggregation between nodes is completed in terms of the convolution theorem to the graph signal. The graph convolutional neural network becomes an effective way of graph data related modeling. Most existing models have only two or three layers of shallow model architecture due to the challenge of over-smoothing phenomenon of deep layer graph structure. The over-smoothing phenomenon is that the graph convolutional neural network fuses node features smoothly via replicable Laplacian applications from different neighborhoods. The smoothing operation makes the vertex features of the same cluster be similar

which simplifies the classification task. But

the expression of each node tends to converge to a certain value in the graph when the number of layers is deepened

and the vertices become indistinguishable in different clusters. Existing researches have shown that graph convolution is similar to a local filter

which is a linear combination of feature vectors of neighboring neighbors. A shallow graph convolutional neural network cannot transmit the full label information to the entire graph with only a few labels

which cannot explore the global graph structure in the graph convolutional neural network. At the same time

deep graph convolutional neural networks require a larger receiving domain. One of the key advantages provided by deep architecture in computer vision is that they can compose complex functions from simple structures. Inspired by the convolutional neural network

the deep structure of the graph convolutional neural network can obtain more node representation information theoretically

so many researchers conduct in-depth research on its hierarchical information. According to the aggregation and transmission features of the graph convolutional neural network algorithm

the core of transferring hierarchical structure algorithms to graph data analysis lies in the construction of layer-level convolution operators and the fusion of information between layer levels. We review the graph network level information mining algorithms. First

we discuss the current situation and existing issues of graph convolutional neural networks

and then introduce the development of graph convolutional neural network hierarchy algorithms

and propose a new category method in term of the different layer information processing of graph convolution. Existing algorithms are divided into regularization methods and architecture adjustment methods. Regular methods focus on the construction of layer-level convolution operators. To deepen the graph neural network and slow down the occurrence of over-smoothing graph structure relationships are used to constrain the information transmission in the convolution process. Next

architecture adjustment methods are based on information fusion between levels to enrich the representation of nodes

including various residual connections like knowledge jumps or affine skip connections. At the same time

we demonstrate that the hierarchical feature nodes are obtained in the graph structure through the hierarchical features experiment. The hierarchical feature nodes can only be classified by the graph convolutional neural network at the corresponding depth. The graph network hierarchical information mining algorithm uses different data mining methods to classify different characteristic nodes via a unified model and an end-to-end paradigm. If there is a model that can classify hierarchical feature nodes at each level successfully

the task of graph network node classification will make good result. Finally

the main application fields of the graph convolutional neural network hierarchical information mining model are summarized

and the future research direction are predicted from four aspects of computing efficiency

large-scale data

dynamic graphs and application scenarios. Graph network hierarchical information mining is a deeper exploration of graph neural networks. The hierarchical information interaction

transfer and dynamic evolution can obtain the richer node information from the shallow to deep information of the graph neural network. We clarify the adopted issue of deep structured graph neural networks further. The effectiveness of information mining issue between levels has to be developed further although some of hierarchical graph convolutional network algorithms can slow down the occurrence of over-smoothing.

关键词

Keywords

references

Abu-El-Haija S, Kapoor A, Perozzi B and Lee J. 2020. N-GCN: multi-scale graph convolution for semi-supervised node classification//Proceedings of the 35th Uncertainty in Artificial Intelligence Conference. Tel Aviv, Israel: PMLR: 841-851

Abu-El-Haija S, Perozzi B, Kapoor A, Alipourfard N, Lerman K, Harutyunyan H, Ver Steeg G and Galstyan A. 2019. MixHop: higher-order graph convolutional architectures via sparsified neighborhood mixing//Proceedings of the 36th International Conference on Machine Learning. Long Beach, USA: PMLR: 21-29

Bian T, Xiao X, Xu T Y, Zhao P L, Huang W B, Rong Y and Huang J Z. 2020. Rumor detection on social media with bi-directional graph convolutional networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1): 549-556 [DOI: 10.1609/aaai.v34i01.5393]

Bianchi F M, Grattarola D, Livi L and Alippi C. 2022. Graph neural networks with convolutional ARMA filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7): 3496-3507 [DOI: 10.1109/TPAMI.2021.3054830]

Bondy J A and Murty U S R. 1976. Graph Theory with Applications. London, UK: MacMillan

Bruna J, Zaremba W, Szlam A and LeCun Y. 2014. Spectral networks and deep locally connected networks on graphs//Proceedings of the 2nd International Conference on Learning Representations. Banff, Canada: ICLR: 1-14

Chen L, Wu L, Hong R C, Zhang K and Wang M. 2020a. Revisiting graph based collaborative filtering: a linear residual graph convolutional network approach. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1): 27-34 [DOI: 10.1609/aaai.v34i01.5330]

Chen M, Wei Z Z, Huang Z F, Ding B L and Li Y L. 2020b. Simple and deep graph convolutional networks//Proceedings of the 37th International Conference on Machine Learning. Virtual: PMLR, 119: 1725-1735

Chen W Q, Chen L, Xie Y, Cao W, Gao Y S and Feng X J. 2020c. Multi-range attentive bicomponent graph convolutional network for traffic forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 34(4): 3529-3536 [DOI:10.1609/aaai.v34i04.5758]

Chen X L, Li L J, Li F F and Gupta A. 2018. Iterative visual reasoning beyond convolutions//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 7239-7248 [ DOI: 10.1109/CVPR.2018.00756 http://dx.doi.org/10.1109/CVPR.2018.00756 ]

Chen Y P, Rohrbach M, Yan Z C, Shuicheng Y, Feng J S and Kalantidis Y. 2019. Graph-based global reasoning networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 433-442 [ DOI: 10.1109/CVPR.2019.00052 http://dx.doi.org/10.1109/CVPR.2019.00052 ]

Defferrard M, Bresson X and Vandergheynst P. 2016. Convolutional neural networks on graphs with fast localized spectral filtering//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain: Curran Associates Inc. : 3844-3852

Dehmamy N, Barabási A-L and Yu R. 2019. Understanding the representation power of graph neural networks in learning graph topology//Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates, Inc. : 15413-15423

Fey M and Lenssen J E. 2019. Fast graph representation learning with PyTorch Geometric [EB/OL]. [2021-08-22] . https://arxiv.org/pdf/1903.02428.pdf https://arxiv.org/pdf/1903.02428.pdf

Gardner M W and Dorling S R. 1998. Artificial neural networks (the multilayer perceptron) — a review of applications in the atmospheric sciences. Atmospheric Environment, 32(14/15): 2627-2636 [DOI: 10.1016/S1352-2310(97)00447-0]

Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial networks//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press: 2672-2680

Hamilton W L, Ying R and Leskovec J. 2017. Inductive representation learning on large graphs//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA: Curran Associates Inc. : 1025-1035

Hammond D K, Vandergheynst P and Gribonval R. 2011. Wavelets on graphs via spectral graph theory. Applied and Computational Harmonic Analysis, 30(2): 129-150 [DOI: 10.1016/j.acha.2010.04.005]

He X N, Deng K, Wang X, Li Y, Zhang Y D and Wang M. 2020. LightGCN: simplifying and powering graph convolution network for recommendation//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi′an, China: ACM: 639-648 [ DOI: 10.1145/3397271.3401063 http://dx.doi.org/10.1145/3397271.3401063 ]

Huang G, Liu Z, Van Der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 2261-2269 [ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]

Huang K X and Zitnik M. 2020. Graph meta learning via local subgraphs//Proceedings of the 34th Conference on Neural Information Processing Systems, Vancouver, Canada: Curran Associates, Inc. 33: 5862-5874

Kipf T N and Welling M. 2017. Semi-supervised classification with graph convolutional networks//Proceedings of the 5th International Conference on Learning Representations. Toulon, France: ICLR: 1-14

Klicpera J, Bojchevski A and Günnemann S. 2019a. Predict then propagate: graph neural networks meet personalized pagerank//Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: ICLR: 1-15

Klicpera J, Weißenberger S and Günnemann S. 2019b. Diffusion improves graph learning//Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates, Inc. : 13366-13378

Krizhevsky A, Sutskever I and Hinton G E. 2012. Imagenet classification with deep convolutional neural networks//Proceedings of the 25th International Conferenceon Neural Information Processing Systems. Lake Tahoe, USA: Curran Associates Inc. : 1097-1105

Lawler G F and Limic V. 2010. Random Walk: A Modern Introduction. Cambridge: Cambridge University Press [DOI: 10.1017/CBO9780511750854]

Lee C W, Fang W, Yeh C K and Wang Y C F. 2018. Multi-label zero-shot learning with structured knowledge graphs//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 1576-1585 [ DOI: 10.1109/CVPR.2018.00170 http://dx.doi.org/10.1109/CVPR.2018.00170 ]

Li C and Goldwasser D. 2019a. Encoding social information with graph convolutional networks forpolitical perspective detection in news media//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy: Association for Computational Linguistics: 2594-2604 [ DOI: 10.18653/v1/P19-1247 http://dx.doi.org/10.18653/v1/P19-1247 ]

Li G H, Müller M, Thabet A and Ghanem B. 2019b. DeepGCNs: can GCNs go as deep as CNNs?//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South): IEEE: 9267-9276 [ DOI: 10.1109/ICCV.2019.00936 http://dx.doi.org/10.1109/ICCV.2019.00936 ]

Li Q M, Han Z C and Wu X M. 2018. Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1): 3538-3545

Li S Z. 1994. Markov random field models in computer vision//Proceedings of the 3rd European Conference on Computer Vision. Stockholm, Sweden: Springer: 361-370 [ DOI: 10.1007/BFb0028368 http://dx.doi.org/10.1007/BFb0028368 ]

Lin T Y, Dollár P, Girshick R, He K M, Hariharan B and Belongie S. 2017. Feature pyramid networks for object detection//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 936-944 [ DOI: 10.1109/CVPR.2017.106 http://dx.doi.org/10.1109/CVPR.2017.106 ]

Lin Y L and Skiena S S. 1995. Algorithms for square roots of graphs. SIAM Journal on Discrete Mathematics, 8(1): 99-118 [DOI: 10.1137/S089548019120016X]

Liu L, Zhou T Y, Long G D, Jiang J, Yao L N and Zhang C Q. 2019a. Prototype propagation networks (PPN) for weakly-supervised few-shot learning on category graph//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Macao, China: IJCAI: 3015-3022 [ DOI: 10.24963/ijcai.2019/418 http://dx.doi.org/10.24963/ijcai.2019/418 ]

Liu X J, Gao F Y, Zhang Q and Zhao H S. 2019b. Graph convolution for multimodal information extraction from visually rich documents//Proceedings of 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers). Minneapolis, Minnesota, USA: Association for Computational Linguistics: 32-39 [ DOI: 10.18653/v1/N19-2005 http://dx.doi.org/10.18653/v1/N19-2005 ]

Loukas A. 2019. What graph neural networks cannot learn: depth vs width [EB/OL]. [2021-08-23] . https://arxiv.org/pdf/1907.03199.pdf https://arxiv.org/pdf/1907.03199.pdf

Narang S K, Gadde A and Ortega A. 2013. Signal processing techniques for interpolation in graph structured data//Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, Canada: IEEE: 5445-5449 [ DOI: 10.1109/ICASSP.2013.6638704 http://dx.doi.org/10.1109/ICASSP.2013.6638704 ]

Nt H and Maehara T. 2019. Revisiting graph neural networks: all we have is low-pass filters [EB/OL]. [2021-08-23] . https://arxiv.org/pdf/1905.09550.pdf https://arxiv.org/pdf/1905.09550.pdf

Page L, Brin S, Motwani R and Winograd T. 1999. The PageRank Citation Ranking: Bringing Order to the Web. Stanford InfoLab. : 1-17

Pei Y L, Huang T J, van Ipenburg W and Pechenizkiy M. 2022. ResGCN: attention-based deep residual modeling for anomaly detection on attributed networks. Machine Learning, 111(2): 519-541

Peng H, Li J X, Gong Q R, Song Y Q, Ning Y X, Lai K F and Yu P S. 2019. Fine-grained event categorization with heterogeneous graph convolutional networks//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Macao, China: AAAI: 3238-3245

Perozzi B, Al-Rfou R and Skiena S. 2014. DeepWalk: online learning of social representations//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM: 701-710 [ DOI: 10.1145/2623330.2623732 http://dx.doi.org/10.1145/2623330.2623732 ]

Qi S Y, Wang W G, Jia B X, Shen J B and Zhu S C. 2018. Learning human-object interactions by graph parsing neural networks//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany: Springer: 407-423 [ DOI: 10.1007/978-3-030-01240-3_25 http://dx.doi.org/10.1007/978-3-030-01240-3_25 ]

Qi X J, Liao R J, Jia J Y, Fidler S and Urtasun R. 2017. 3D graph neural networks for RGBD semantic segmentation//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 5209-5218 [ DOI: 10.1109/ICCV.2017.556 http://dx.doi.org/10.1109/ICCV.2017.556 ]

Qiu J Z, Tang J, Ma H, Dong Y X, Wang K S and Tang J. 2018. DeepInf: social influence prediction with deep learning//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London, UK: ACM: 2110-2119 [ DOI: 10.1145/3219819.3220077 http://dx.doi.org/10.1145/3219819.3220077 ]

Rong Y, Huang W B, Xu T Y and Huang J Z. 2020. DropEdge: towards deep graph convolutional networks on node classification//Proceedings of the 7th International Conference on Learning Representations. 1-17

Scarselli F, Gori M, Tsoi A C, Hagenbuchner M and Monfardini G. 2009. The graph neural network model. IEEE Transactions on Neural Networks, 20(1): 61-80 [DOI: 10.1109/TNN.2008.2005605]

Song L, Wang Z, Yu M, Zhang Y, Florian R and Gildea D. 2018. Exploring graph-structured passage representation for multi-hop reading comprehension with graph neural networks [EB/OL]. [2021-08-23] . https://arxiv.org/pdf/1809.02040.pdf https://arxiv.org/pdf/1809.02040.pdf

Spinelli I, Scardapane S and Uncini A. 2021. Adaptive propagation graph convolutional network. IEEE Transactions on Neural Networks and Learning Systems, 32(10): 4755-4760 [DOI: 10.1109/TNNLS.2020.3025110]

Sun K, Lin Z X and Zhu Z C. 2021. AdaGCN: adaboosting graph convolutional networks into deep models [EB/OL]. [2021-08-23] . https://arxiv.org/pdf/1908.05081.pdf https://arxiv.org/pdf/1908.05081.pdf

Taubin G. 1995. A signal processing approach to fair surface design//Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques. New York, USA: ACM: 351-358 [ DOI: 10.1145/218380.218473 http://dx.doi.org/10.1145/218380.218473 ]

Valsesia D, Fracastoro G and Magli E. 2019. Learning localized generative models for 3D point clouds via graph convolution///Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: [s. n.]: 1-15

Veličković P, Cucurull G, Casanova A, Romero A, Lio P and Bengio Y. 2018. Graph attention networks//Proceedings of the 6th International Conference on Learning Representations. Vancouver, Canana. [s. n.]. 1-12

Wang D, Jamnik M and Lio P. 2020. Abstract diagrammatic reasoning with multiplex graph networks//Proceedings of the 8th International Conference on Learning Representations. Addis Ababa, Ethiopia: [s. n.]: 1-20

Wang H, Xu T, Liu Q, Lian D F, Chen E H, Du D F, Wu H and Su W. 2019. MCNE: an end-to-end framework for learning multiple conditional network representations of social network//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Anchorage, USA: ACM: 1064-1072 [ DOI: 10.1145/3292500.3330931 http://dx.doi.org/10.1145/3292500.3330931 ]

Wang J Y and Deng Z D. 2021. A deep graph wavelet convolutional neural network for semi-supervised node classification//Proceedings of 2021 International Joint Conference on Neural Networks. Shenzhen, China: ACM: 1-8

Wang Y Q and Karaletsos T. 2021. Stochastic aggregation in graph neural networks [EB/OL]. [2021-08-25] . https://arxiv.org/pdf/2102.12648.pdf https://arxiv.org/pdf/2102.12648.pdf

Wu F, Souza A, Zhang T Y, Fifty C, Yu T and Weinberger K. 2019. Simplifying graph convolutional networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach, USA: PMLR: 6861-6871

Wu Y J, Lian D F, Xu Y H, Wu L and Chen E H. 2020. Graph convolutional networks with Markov random field reasoning for social spammer detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1): 1054-1061

Wu Z H, Pan S R, Chen F W, Long G D, Zhang C Q and Yu P S. 2021. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1): 4-24 [DOI: 10.1109/TNNLS.2020.2978386]

Xu B B, Cen K T, Huang J J, Shen H W and Cheng X Q. 2020. A survey on graph convolutional neural network. Chinese Journal of Computers, 43(5): 755-780

徐冰冰, 岑科廷, 黄俊杰, 沈华伟, 程学旗. 2020. 图卷积神经网络综述. 计算机学报, 43(5): 755-780

Xu B B, Shen H W, Cao Q, Qiu Y Q and Cheng X Q. 2019. Graph wavelet neural network [EB/OL]. [2021-08-25] . https://arxiv.org/pdf/1904.07785.pdf https://arxiv.org/pdf/1904.07785.pdf

Xu K, Li C T, Tian Y L, Sonobe T, Kawarabayashi K I and Jegelka S. 2018. Representation learning on graphs with jumping knowledge networks//Proceedings of the 35th International Conference on Machine Learning. Stockholm, Sweden: PMLR: 5453-5462

Yan S J, Xiong Y J and Lin D H. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. Proceedings of the AAAI conference on artificial intelligence, 32(1): 7444-7452

Yang Z L, Cohen W W and Salakhutdinov R. 2016. Revisiting semi-supervised learning with graph embeddings//Proceedings of the 33rd International Conference on International Conference on Machine Learning. New York, USA: JMLR: 40-48

Ying R, He R N, Chen K F, Eksombatchai P, Hamilton W L and Leskovec J. 2018. Graph convolutional neural networks for web-scale recommender systems//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London, UK: ACM: 974-983 [ DOI: 10.1145/3219819.3219890 http://dx.doi.org/10.1145/3219819.3219890 ]

Zhang C, Lin G S, Liu F Y, Guo J S, Wu Q Y and Yao R. 2019a. Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea (South): IEEE: 9586-9594 [ DOI: 10.1109/ICCV.2019.00968 http://dx.doi.org/10.1109/ICCV.2019.00968 ]

Zhang H M and Xu M. 2021. SSFG: stochastically scaling features and gradients for regularizing graph convolution networks [EB/OL]. [2021-08-20] . https://arxiv.org/pdf/2102.10338.pdf https://arxiv.org/pdf/2102.10338.pdf

Zhang J N, Shi X J, Zhao S L and King I. 2019b. STAR-GCN: stacked and reconstructed graph convolutional networks for recommender systems//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Macao, China: AAAI: 4264-4270

Zhang J J, Wu Q, Zhang J, Shen C H and Lu J F. 2019c. Mind your neighbours: image annotation with metadata neighbourhood graph co-attention networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE: 2956-2964 [ DOI: 10.1109/CVPR.2019.00307 http://dx.doi.org/10.1109/CVPR.2019.00307 ]

Zhang M H and Chen Y X. 2018. Link prediction based on graph neural networks//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal, Canada: Curran Associates Inc. : 5171-5181

Zhang S Y, He X M and Yan S P. 2019 d. LatentGNN: learning efficient non-local relations for visual recognition//Proceedings of the 36th International Conference on Machine Learning. Long Beach, California, USA: PMLR: 7374-7383

Zhang Z L, Zhang Y J, Feng R, Zhang T and Fan W G. 2020. Zero-shot sketch-based image retrieval via graph convolution network. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7): 12943-12950 [DOI: 10.1609/aaai.v34i07.6993]

Zhao L X and Akoglu L. 2019. PairNorm: tackling oversmoothing in GNNs [EB/OL]. [2021-08-25] . https://arxiv.org/pdf/1909.12223.pdf https://arxiv.org/pdf/1909.12223.pdf

Zhou Z P and Li X C. 2017. Graph convolution: a high-order and adaptive approach [EB/OL]. [2021-08-29] . https://arxiv.org/pdf/1706.09916.pdf https://arxiv.org/pdf/1706.09916.pdfv

Zhu H and Koniusz P. 2020. Simple spectral graph convolution//Proceedings of the 8th International Conference on Learning Representations. Addis Ababa, Ethiopia: [s. n.]: 1-15