山西大学 计算机与信息技术学院,山西 太原 030006
崔致林,山西大学计算机与信息技术学院硕士研究生。主要研究方向为图数据挖掘等。
郭虎升,博士,教授,博士生导师,三晋英才青年优秀人才。中国计算机学会杰出会员、中国计算机学会人工智能与模式识别专委会执行委员,中国人工智能学会机器学习专委会委员、知识工程专委会委员。担任多个国际国内学术会议的出版主席、论坛主席、程序委员。近年来,主持国家自然科学基金项目2项,省部级项目10余项。曾荣获山西省科技进步二等奖、教育部宝钢教育奖、山西大学十佳青年教师、ACM理事会太原分会优博。主要研究方向为数据挖掘、机器学习等。
收稿:2025-09-19,
修回:2026-02-24,
纸质出版:2026-06-25
移动端阅览
崔致林,郭虎升.图神经网络综述:从静态建模到动态演化[J].新兴科学和技术趋势,2026,5(2):141-159.
CUI Zhilin,GUO Husheng.A survey of Graph Neural Network: from static modelling to dynamic evolution[J].Emerging Science and Technology,2026,5(2):141-159.
崔致林,郭虎升.图神经网络综述:从静态建模到动态演化[J].新兴科学和技术趋势,2026,5(2):141-159. DOI: 10.12405/j.issn.2097-1486.2026.02.004.
CUI Zhilin,GUO Husheng.A survey of Graph Neural Network: from static modelling to dynamic evolution[J].Emerging Science and Technology,2026,5(2):141-159. DOI: 10.12405/j.issn.2097-1486.2026.02.004.
图神经网络(Graph Neural Network,GNN)是一类用于处理图数据结构的深度学习模型,因其在处理非欧式空间数据和复杂特征方面的优势,受到广泛关注,并被广泛应用于推荐系统、知识图谱、交通道路分析等领域。GNN通过结合图结构中节点和边的信息,能够有效地学习图的表示。这些方法可以应用于静态图和动态图中,静态图是指一个单一且固定的图结构,而动态图会随着时间的推移发生变化。本文首先介绍了从卷积神经网络(Convolutional Neural Networks,CNN)到图神经网络(GNN)的发展历程,接着介绍了一些图表示的基本概念。然后,本文讨论了图神经网络的基本任务,并根据其消息传递机制介绍了常见的图神经网络模型。针对动态图的处理,本文根据动态性粒度将图神经网络分为离散型和连续型两类。最后,本文对图神经网络所面临的挑战及未来研究方向进行了展望。
Graph Neural Network (GNN) is a deep learning model for processing graph data structures. It has garnered widespread attention due to its ability to handle non-Euclidean spatial data and complex features and has been widely applied in recommendation systems, knowledge graphs, and traffic analysis. By integrating node and edge information within graph structures, GNN effectively learn graph representations. These methods can be applied to both static and dynamic graphs: static graphs denote a single, fixed structure, while dynamic graphs undergo changes over time. This paper first outlines the evolutionary trajectory from Convolutional Neural Networks (CNN) to GNN, followed by an introduction to fundamental concepts in graph representation. Subsequently, the paper discusses fundamental tasks for GNN and introduces common models based on their message-passing mechanisms. For dynamic graph processing, GNN are categorised into discrete and continuous types according to the granularity of dynamic changes. Finally, the paper provides an outlook for future research directions.
Zeng Yuansong , Zhou Xiang , Rao Jiahua , et al . Accurately clustering single-cell RNA-seq data by capturing structural relations between cells through graph convolutional network [C]// 2020 IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM) , 2020 : 519 - 522 .
Chen Cen , Li Kenli , Teo S G , et al . Citywide traffic flow prediction based on multiple gated spatio-temporal convolutional neural networks [J]. ACM Transactions on Knowledge Discovery from Data (TKDD) , 2020 , 14 ( 4 ): 1 - 23 . DOI: 10.1145/3385414 http://dx.doi.org/10.1145/3385414 .
Zehmakan A N . Majority opinion diffusion in social networks: An adversarial approach [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2021 : 5611 - 5619 .
Chen Jianguo , Li Kenli , Bilal K , et al . A bi-layered parallel training architecture for large-scale convolutional neural networks [J]. IEEE Transactions on Parallel and Distributed Systems , 2018 , 30 ( 5 ): 965 - 976 . DOI: 10.1109/TPDS.2018.2877359 http://dx.doi.org/10.1109/TPDS.2018.2877359 .
Pu Bin , Li Kenli , Li Shengli , et al . Automatic fetal ultrasound standard plane recognition based on deep learning and IIoT [J]. IEEE Transactions on Industrial Informatics , 2021 , 17 ( 11 ): 7771 - 7780 . DOI: 10.1109/TII.2021.3069470 http://dx.doi.org/10.1109/TII.2021.3069470 .
Gori M , Monfardini G , Scarselli F . A new model for learning in graph domains [C]// Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005 , 2 : 729 - 734 .
Scarselli F , Gori M , Tsoi A C , et al . The graph neural network model [J]. IEEE Transactions on Neural Networks , 2008 , 20 ( 1 ): 61 - 80 . DOI: 10.1109/TNN.2008.2005605 http://dx.doi.org/10.1109/TNN.2008.2005605 .
He Xiangnan , Deng Kuan , Wang Xiang , et al . Lightgcn: Simplifying and powering graph convolution network for recommendation [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval , 2020 : 639 - 648 .
Ji Shaoxiong , Pan Shirui , Cambria E , et al . A survey on knowledge graphs: Representation, acquisition, and applications [J]. IEEE Transactions on Neural Networks and Learning Systems , 2021 , 33 ( 2 ): 494 - 514 . DOI: 10.1109/TNNLS.2021.3070843 http://dx.doi.org/10.1109/TNNLS.2021.3070843 .
Ji Guoliang , Liu Kang , He Shizhu , et al . Knowledge graph completion with adaptive sparse transfer matrix [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2016 : 1304 - 1310 .
Chen Cen , Li Kenli , Teo S G , et al . Gated residual recurrent graph neural networks for traffic prediction [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2019 : 485 - 492 .
Zhou Jie , Cui Ganqu , Hu Shengding , et al . Graph neural networks: A review of methods and applications [J]. AI Open , 2020 , 1 : 57 - 81 . DOI: 10.1016/j.aiopen.2021.01.001 http://dx.doi.org/10.1016/j.aiopen.2021.01.001 .
Zhang Ziwei , Cui Peng , Zhu Wenwu . Deep learning on graphs: A survey [J]. IEEE Transactions on Knowledge and Data Engineering , 2020 , 34 ( 1 ): 249 - 270 . DOI: 10.1109/TKDE.2020.2981333 http://dx.doi.org/10.1109/TKDE.2020.2981333 .
Hamilton W L , Ying R , Leskovec J . Representation learning on graphs: Methods and applications [PP/OL]. arXiv preprint ( 2017-09-17 )[ 2025-08-17 ]. https://arxiv.org/abs/1709.05584 https://arxiv.org/abs/1709.05584 .
Skarding J , Gabrys B , Musial K . Foundations and modeling of dynamic networks using dynamic graph neural networks: A survey [J]. IEEE Access , 2021 , 9 : 79143 - 79168 . DOI: 10.1109/ACCESS.2021.3082932 http://dx.doi.org/10.1109/ACCESS.2021.3082932 .
Md V , Misra S , Ma G , et al . Distgnn: Scalable distributed training for large-scale graph neural networks [C]// Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis , 2021 : 1 - 14 .
Yang Carl , Xiao Yuxin , Zhang Yu , et al . Heterogeneous network representation learning: A unified framework with survey and benchmark [J]. IEEE Transactions on Knowledge and Data Engineering , 2020 , 34 ( 10 ): 4854 - 4873 . DOI: 10.1109/TKDE.2020.3045924 http://dx.doi.org/10.1109/TKDE.2020.3045924 .
Goyal P , Ferrara E . Graph embedding techniques, applications, and performance: A survey [J]. Knowledge-Based Systems , 2018 , 151 : 78 - 94 . DOI: 10.1016/j.knosys.2018.03.022 http://dx.doi.org/10.1016/j.knosys.2018.03.022 .
Roweis S T , Saul L K . Nonlinear dimensionality reduction by locally linear embedding [J]. Science , 2000 , 290 ( 5500 ): 2323 - 2326 . DOI: 10.1126/science.290.5500.2323 http://dx.doi.org/10.1126/science.290.5500.2323 .
Belkin M , Niyogi P . Laplacian eigenmaps and spectral techniques for embedding and clustering [C]// Advances in Neural Information Processing Systems 14 . Cambridge : MIT Press , 2001 : 585 - 591 .
Von Luxburg U . A tutorial on spectral clustering [J]. Statistics and Vomputing , 2007 , 17 ( 4 ): 395 - 416 . DOI: 10.1007/s11222-007-9033-z http://dx.doi.org/10.1007/s11222-007-9033-z .
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 , 2014 : 701 - 710 .
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 , 2016 : 855 - 864 .
Ying R , You Jiaxuan , Morris C , et al . Hierarchical graph representation learning with differentiable pooling [C]// 32nd Conference on Neural Information Processing Systems (NIPS) , 2018 : 4805 - 4815 .
Borgwardt K M , Kriegel H P . Shortest-path kernels on graphs [C]// Fifth IEEE International Conference on Data Mining (ICDM'05) , 2005 : 74 - 81 .
Shervashidze N , Schweitzer P , Van Leeuwen E J , et al . Weisfeiler-lehman graph kernels [J]. Journal of Machine Learning Research , 2011 , 12 : 2539 - 2561 . DOI: 10.5555/1953048.2078187 http://dx.doi.org/10.5555/1953048.2078187 .
Feng Aosong , You Chenyu , Wang Shiqiang , et al . Kergnns: Interpretable graph neural networks with graph kernels [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 6 ): 6614 - 6622 .
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 , 2016 : 3844 - 3852 .
Bruna J , Zaremba W , Szlam A , et al . Spectral networks and deep locally connected networks on graphs [C]// 2nd International Conference on Learning Representations , ICLR 2014 , 2014 .
Li Ruoyu , Wang Sheng , Zhu Feiyun , et al . Adaptive graph convolutional neural networks [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2018 : 3546 - 3553 .
Levie R , Monti F , Bresson X , et al . Cayleynets: Graph convolutional neural networks with complex rational spectral filters [J]. IEEE Transactions on Signal Processing , 2018 , 67 ( 1 ): 97 - 109 . DOI: 10.1109/TSP.2018.2879624 http://dx.doi.org/10.1109/TSP.2018.2879624 .
Bianchi F M , Grattarola D , Livi L , et al . Graph neural networks with convolutional arma filters [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 44 ( 7 ): 3496 - 3507 . DOI: 10.1109/TPAMI.2021.3054830 http://dx.doi.org/10.1109/TPAMI.2021.3054830 .
Xu Keyulu , Hu Weihua , Leskovec J , et al . How Powerful are Graph Neural Networks? [C]// International Conference on Learning Representations , 2018 .
Duvenaud D K , Maclaurin D , Iparraguirre J , et al . Convolutional networks on graphs for learning molecular fingerprints [PP/OL]. arXiv ( 2015-09-30 )[ 2025-08-17 ]. https://doi.org/10.48550/arXiv.1509.09292 https://doi.org/10.48550/arXiv.1509.09292 .
Niepert M , Ahmed M , Kutzkov K . Learning convolutional neural networks for graphs [C]// International Conference on Machine Learning , 2016 : 2014 - 2023 .
Atwood J , Towsley D . Diffusion-convolutional neural networks [C]// Advances in Neural Information Processing Systems , 2016 .
Gasteiger J , Bojchevski A , Günnemann S . Predict then Propagate: Graph Neural Networks meet Personalized PageRank [C]// International Conference on Learning Representations , 2018 .
Kipf T N , Welling M . Semi-supervised classification with graph convolutional networks [PP/OL]. arXiv preprint ( 2016-09-09 )[ 2025-08-17 ]. https://arxiv.org/abs/1609.02907 https://arxiv.org/abs/1609.02907 .
Velickovic P , Cucurull G , Casanova A , et al . Graph attention networks [C]// International Conference on Learning Representations , 2018 .
Hamilton W , Ying Z , Leskovec J . Inductive representation learning on large graphs [PP/OL]. arXiv ( 2017-06-07 ) [ 2025-08-17 ]. https://doi.org/10.48550/arXiv.1706.02216 https://doi.org/10.48550/arXiv.1706.02216 .
Gao Hongyang , Wang Zhengyang , Ji Shuiwang . Large-scale learnable graph convolutional networks [C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , 2018 : 1416 - 1424 .
Monti F , Boscaini D , Masci J , et al . Geometric deep learning on graphs and manifolds using mixture model cnns [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 5115 - 5124 .
Xu Keyulu , Li Chengtao , Tian Yonglong , et al . Representation learning on graphs with jumping knowledge networks [C]// International Conference on Machine Learning , 2018 : 5453 - 5462 .
Zhang Zhaoli , Li Zhifei , Liu Hai , et al . Multi-scale dynamic convolutional network for knowledge graph embedding [J]. IEEE Transactions on Knowledge and Data Engineering , 2020 , 34 ( 5 ): 2335 - 2347 . DOI: 10.1109/TKDE.2020.3005952 http://dx.doi.org/10.1109/TKDE.2020.3005952 .
Zhang Muhan , Chen Yixin . Weisfeiler-lehman neural machine for link prediction [C]// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , 2017 : 575 - 583 .
Zhang Muhan , Chen Yixin . Link prediction based on graph neural networks [C]// Advances in Neural Information Processing Systems , 2018 : 5165 - 5175 .
Chen Jie , Ma Tengfei , Xiao Cao . Fastgcn: fast learning with graph convolutional networks via importance sampling [PP/OL]. arXiv preprint ( 2018-01-30 )[ 2025-08-17 ]. https://arxiv.org/abs/1801.10247 https://arxiv.org/abs/1801.10247 .
Gao Hongyang , Ji Shuiwang . Graph u-nets [C]// international conference on machine learning , 2019 : 2083 - 2092 .
Gilmer J , Schoenholz S S , Riley P F , et al . Neural message passing for quantum chemistry [C]// International Conference on Machine Learning , 2017 : 1263 - 1272 .
Lee J , Lee I , Kang J . Self-attention graph pooling [C]// International Conference on Machine Learning , 2019 : 3734 - 3743 .
Ma Yao , Wang Suhang , Aggarwal C C , et al . Graph convolutional networks with eigenpooling [C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , 2019 : 723 - 731 .
Yuan Hao , Ji Shuiwang . Structpool: Structured graph pooling via conditional random fields [C]// Proceedings of the 8th International Conference on Learning Pepresentations , 2020 .
Zhang Muhan , Cui Zhicheng , Neumann M , et al . An end-to-end deep learning architecture for graph classification [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2018 : 4438 - 4445 .
Zhuang Chenyi , Ma Qiang . Dual graph convolutional networks for graph-based semi-supervised classification [C]// Proceedings of the 2018 World Wide Web Conference , 2018 : 499 - 508 .
Liu Xiaorui , Jin Wei , Ma Yao , et al . Elastic graph neural networks [C]// International Conference on Machine Learning , 2021 : 6837 - 6849 .
蒋玉英 , 陈心雨 , 李广明 , 等 . 图神经网络及其在图像处理领域的研究进展 [J]. 计算机工程与应用 , 2023 , 59 ( 7 ): 15 - 30 . DOI: 10.3778/j.issn.1002-8331.2205-0503 http://dx.doi.org/10.3778/j.issn.1002-8331.2205-0503 .
Wu Zonghan , Pan Shirui , Chen Fengwen , et al . A comprehensive survey on graph neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , 32 ( 1 ): 4 - 24 . DOI: 10.1109/TNNLS.2020.2978386 http://dx.doi.org/10.1109/TNNLS.2020.2978386 .
Sandryhaila A , Moura J M F . Discrete signal processing on graphs: Graph fourier transform [C]// 2013 IEEE International Conference on Acoustics, Speech and Signal Processing , 2013 : 6167 - 6170 .
Kipf T N , Welling M . Variational graph auto-encoders [PP/OL]. arXiv preprint ( 2016-11-21 )[ 2025-08-17 ]. https://arxiv.org/abs/1611.07308 https://arxiv.org/abs/1611.07308 .
Yu Yong , Si Xiaosheng , Hu Changhua , et al . A review of recurrent neural networks: LSTM cells and network architectures [J]. Neural Computation , 2019 , 31 ( 7 ): 1235 - 1270 . DOI: 10.1162/neco_a_01199 http://dx.doi.org/10.1162/neco_a_01199 .
Dey R , Salem F M . Gate-variants of gated recurrent unit (GRU) neural networks [C]// 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS) , 2017 : 1597 - 1600 .
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 . DOI: 10.1016/j.acha.2010.04.005 http://dx.doi.org/10.1016/j.acha.2010.04.005 .
Sardellitti S , Barbarossa S , Di Lorenzo P . On the graph Fourier transform for directed graphs [J]. IEEE Journal of Selected Topics in Signal Processing , 2017 , 11 ( 6 ): 796 - 811 . DOI: 10.1109/JSTSP.2017.2726979 http://dx.doi.org/10.1109/JSTSP.2017.2726979 .
Moser R A , Tardos G . A constructive proof of the general Lovász local lemma [J]. Journal of the ACM , 2010 , 57 ( 2 ): 1 - 15 . DOI: 10.1145/1667053.1667060 http://dx.doi.org/10.1145/1667053.1667060 .
Banerjee A , Merugu S , Dhillon I S , et al . Clustering with Bregman divergences [J]. Journal of Machine Learning Research , 2005 , 6 : 1705 - 1749 . DOI: 10.5555/1046920.1194902 http://dx.doi.org/10.5555/1046920.1194902 .
Micheli A . Neural network for graphs: A contextual constructive approach [J]. IEEE Transactions on Neural Networks , 2009 , 20 ( 3 ): 498 - 511 . DOI: 10.1109/TNN.2008.2010350 http://dx.doi.org/10.1109/TNN.2008.2010350 .
Yan Sijie , Xiong Yuanjun , Lin Dahua . Spatial temporal graph convolutional networks for skeleton-based action recognition [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2018 : 7444 - 7452 .
Gilmer J , Schoenholz S S , Riley P F , et al . Message passing neural networks [J]. Machine Learning Meets Quantum Physics , 2020 : 199 - 214 . DOI: 10.1007/978-3-030-40245-7_10 http://dx.doi.org/10.1007/978-3-030-40245-7_10 .
Li Yujia , Tarlow D , Brockschmidt M , et al . Gated graph sequence neural networks [PP/OL]. arXiv preprint ( 2015-11-17 )[ 2025-08-17 ]. https://arxiv.org/abs/1511.05493 https://arxiv.org/abs/1511.05493 .
Pan Shirui , Hu Ruiqi , Long Guodong , et al . Adversarially regularized graph autoencoder for graph embedding [PP/OL]. arXiv preprint ( 2018-02-13 )[ 2025-08-17 ]. DOI: https://arxiv.org/abs/1802.04407 http://dx.doi.org/https://arxiv.org/abs/1802.04407 .
Manessi F , Rozza A , Manzo M . Dynamic graph convolutional networks [J]. Pattern Recognition , 2020 , 97 : 107000 . DOI: 10.1016/j.patcog.2019.107000 http://dx.doi.org/10.1016/j.patcog.2019.107000 .
Taheri A , Gimpel K , Berger-Wolf T . Learning to represent the evolution of dynamic graphs with recurrent models [C]// Companion Proceedings of the 2019 World Wide Web Conference , 2019 : 301 - 307 .
Chen Jinyin , Wang Xueke , Xu Xuanheng . GC-LSTM: Graph convolution embedded LSTM for dynamic network link prediction [J]. Applied Intelligence , 2022 , 52 ( 7 ): 7513 - 7528 . DOI: 10.1007/s10489-021-02518-9 http://dx.doi.org/10.1007/s10489-021-02518-9 .
Li Jia , Han Zhichao , Cheng Hong , et al . Predicting path failure in time-evolving graphs [C]// Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining , 2019 : 1279 - 1289 .
Jin W , Qu Meng , Jin Xisen , et al . Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs [C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2020 : 6669 - 6683 .
Bonner S , Atapour-Abarghouei A , Jackson P T , et al . Temporal neighbourhood aggregation: Predicting future links in temporal graphs via recurrent variational graph convolutions [C]// 2019 IEEE international conference on big data (Big Data) , 2019 : 5336 - 5345 .
Pareja A , Domeniconi G , Chen Jie , et al . Evolvegcn: Evolving graph convolutional networks for dynamic graphs [C]// Proceedings of the AAAI conference on artificial intelligence , 2020 , 34 ( 4 ): 5363 - 5370 .
Ma Yao , Guo Ziyi , Ren Zhaochun , et al . Streaming graph neural networks [C]// Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval , 2020 : 719 - 728 .
Kumar S , Zhang Xikun , Leskovec J . Predicting dynamic embedding trajectory in temporal interaction networks [C]// Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining , 2019 : 1269 - 1278 .
Trivedi R , Dai Hanjun , Wang Yichen , et al . Know-evolve: Deep temporal reasoning for dynamic knowledge graphs [C]// International Conference on Machine Learning , 2017 : 3462 - 3471 .
Trivedi R , Farajtabar M , Biswal P , et al . Dyrep: Learning representations over dynamic graphs [C]// International Conference on Learning Representations , 2019 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621