图神经网络在多变量时间序列分类中的应用:综述
Application of graph neural network in multivariate time series classification: an overview
- 2026年 页码:1-30
收稿:2025-10-26,
修回:2026-02-28,
录用:2026-03-09,
网络首发:2026-03-09
DOI: 10.11834/jig.250529
移动端阅览

浏览全部资源
扫码关注微信
收稿:2025-10-26,
修回:2026-02-28,
录用:2026-03-09,
网络首发:2026-03-09,
移动端阅览
多变量时间序列(MTS)分类是数据科学中的一项关键任务,旨在从具有复杂时空依赖性的多维数据流中识别模式.近年来,图神经网络(GNN)凭借其强大的结构化数据建模能力,为这一领域带来了范式转变.然而,现有研究呈现出方法多样化但缺乏统一理论指导的局面.本文不仅系统性地梳理了GNN在MTS分类中的应用进展,更重要的是,我们首次提出了一个从“时空依赖耦合范式”(Spatio-Temporal Dependency Coupling Paradigm)角度审视该领域的统一分析框架.该框架将现有模型批判性地划分为解耦式(Decoupled)、耦合式(Coupled)和演化式(Evolutionary)三大类别,深刻揭示了不同设计哲学背后在模型灵活性、计算效率和动态适应性之间的核心权衡.基于此框架,我们超越了对模型机制的简单描述,深入剖析了各类方法在处理现实世界数据中普遍存在的异质性(heterogeneity)、非平稳性(non-stationarity)和因果混淆(causal confounding)等根本性挑战时的内在假设与理论局限.此外,我们通过对交通、医疗、金融和工业等关键应用领域的跨领域综合分析,提炼出驱动模型选择和图构建策略的普适性原则.最后,本文不仅总结了现有挑战,更进一步勾勒出一份旨在构建更鲁棒、可解释和支持干预的下一代时空图智能模型的挑战性研究议程,强调了从关联建模向因果推理演进的必要性.研究表明,GNN在MTS分类中展现的巨大潜力,正推动该领域迈向一个更深刻、更具挑战性的新阶段.
Multi variable time series (MTS) classification is a key task in data science, which aims to identify patterns from multidimensional data streams with complex spatio-temporal dependencies. In recent years, graph neural network (GNN) has brought about a paradigm shift in this field by virtue of its powerful ability to model structured data. However, the existing research shows a situation of diversification of methods but lack of unified theoretical guidance. This paper not only systematically combs the application progress of GNN in MTS classification, but more importantly, we propose a unified analysis framework for the first time to examine this field from the perspective of "Spatial Temporal Dependency Coupling Paradigm". The framework critically divides the existing models into three categories: Decoupled, Coupled and Evolutionary, which profoundly reveals the core trade-offs between model flexibility, computing efficiency and dynamic adaptability behind different design philosophies.Based on this framework, we go beyond the simple description of the model mechanism, and deeply analyze the internal assumptions and theoretical limitations of various methods in dealing with fundamental challenges such as heterogeneity, non-stationary and causal confounding that commonly exist in real world data. In addition, through cross domain comprehensive analysis of key application fields such as transportation, medical care, finance and industry, we extracted the universal principles that drive model selection and graph construction strategies. Finally, this paper not only summarizes the existing challenges, but also further outlines a challenging research agenda aimed at building a more robust, interpretable and supportive next generation spatio-temporal graph intelligent model, emphasizing the necessity of evolving from association modeling to causal reasoning. Research shows that the huge potential of GNN in MTS classification is pushing the field to a deeper and more challenging new stage.
Wei W W S . Multivariate time series analysis and applications [M]. John Wiley & Sons , 2019 .
Ismail Fawaz H , Forestier G , Weber J , et al . Deep learning for time series classification: a review [J]. Data mining and knowledge discovery , 2019 , 33 ( 4 ): 917 - 963 .
Lim B , Zohren S . Time-series forecasting with deep learning: a survey [J]. Philosophical Transactions of the Royal Society A , 2021 , 379 ( 2194 ): 20200209 .
Blázquez-García A , Conde A , Mori U , et al . A review on outlier/anomaly detection in time series data [J]. ACM computing surveys (CSUR) , 2021 , 54 ( 3 ): 1 - 33 .
Liu C L , Hsaio W H , Tu Y C . Time series classification with multivariate convolutional neural network [J]. IEEE Transactions on industrial electronics , 2018 , 66 ( 6 ): 4788 - 4797 .
Gupta A , Gupta H P , Biswas B , et al . An early classification approach for multivariate time series of on-vehicle sensors in transportation [J]. IEEE Transactions on Intelligent Transportation Systems , 2020 , 21 ( 12 ): 5316 - 5327 .
Rodrigues D S , Nastri A C S , Magri M M , et al . Predicting the outcome for COVID-19 patients by applying time series classification to electronic health records [J]. BMC Medical Informatics and Decision Making , 2022 , 22 ( 1 ): 187 .
Selim G E I , Hemdan E Z Z E D , Shehata A M , et al . Anomaly events classification and detection system in critical industrial internet of things infrastructure using machine learning algorithms [J]. Multimedia Tools and Applications , 2021 , 80 ( 8 ): 12619 - 12640 .
Fons E , Dawson P , Zeng X , et al . Evaluating data augmentation for financial time series classification [J]. arXiv preprint arXiv: 2010.15111 , 2020 .
Zhang Z , Zhang K , Khelifi A . Multivariate time series analysis in climate and environmental research [M]. Cham : Springer International Publishing , 2018 .
Berndt D J , Clifford J . Using dynamic time warping to find patterns in time series [C]// Proceedings of the 3rd international conference on knowledge discovery and data mining . 1994 : 359 - 370 .
Ye L , Keogh E . Time series shapelets: a new primitive for data mining [C]// Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining . 2009 : 947 - 956 .
Baydogan M G , Runger G , Tuv E . A bag-of-features framework to classify time series [J ]. IEEE transactions on pattern analysis and machine intelligence , 2013 , 35 ( 11 ): 2796 - 2802 .
Gu J , Wang Z , Kuen J , et al . Recent advances in convolutional neural networks [J]. Pattern recognition , 2018 , 77 : 354 - 377 .
Hochreiter S , Schmidhuber J . Long short-term memory [J]. Neural computation , 1997 , 9 ( 8 ): 1735 - 1780 .
Zhou J , Cui G , Hu S , et al . Graph neural networks: A review of methods and applications [J]. AI open , 2020 , 1 : 57 - 81 .
Fan W , Ma Y , Li Q , et al . Graph neural networks for social recommendation; proceedings of the The world wide web conference, F, 2019 [C].
Gao C , Wang X , He X , et al . Graph neural networks for recommender system; proceedings of the Proceedings of the fifteenth ACM international conference on web search and data mining, F, 2022 [C].
Ye Z , Kumar Y J , Sing G O , et al . A comprehensive survey of graph neural networks for knowledge graphs [J]. IEEE Access , 2022 , 10 : 75729 - 75741 .
Jin G , Liang Y , Fang Y , et al . Spatio-temporal graph neural networks for predictive learning in urban computing: A survey [J]. IEEE Transactions on Knowledge and Data Engineering , 2023 , 36 ( 10 ): 5388 - 5408 .
Bui K H N , Cho J , Yi H . Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues [J]. Applied Intelligence , 2022 , 52 ( 3 ): 2763 - 2774 .
Khodayar M , Wang J . Spatio-temporal graph deep neural network for short-term wind speed forecasting [J]. IEEE Transactions on Sustainable Energy , 2018 , 10 ( 2 ): 670 - 681 .
Qian L , Zuo Q , Liu H , et al . Multivariate time series classification based on spatial-temporal attention dynamic graph neural network [J]. Applied Intelligence , 2025 , 55 ( 2 ): 1 - 18 .
Yuan H , Li G . A survey of traffic prediction: from spatio-temporal data to intelligent transportation [J]. Data Science and Engineering , 2021 , 6 ( 1 ): 63 - 85 .
Liu H , Yang D , Liu X , et al . Todynet: temporal dynamic graph neural network for multivariate time series classification [J]. Information Sciences , 2024 , 677 : 120914 .
Wu Z , Pan S , Chen F , et al . A comprehensive survey on graph neural networks [J]. IEEE transactions on neural networks and learning systems , 2020 , 32 ( 1 ): 4 - 24 .
Zhang S , Tong H , Xu J , et al . Graph convolutional networks: a comprehensive review [J]. Computational Social Networks , 2019 , 6 ( 1 ): 1 - 23 .
Velickovic P , Cucurull G , Casanova A , et al . Graph attention networks [J]. stat , 2017 , 1050 ( 20 ): 10 - 48550 .
Leskovec J . Graphsage: Inductive representation learning on large graphs [J]. SNAP. SNAP , 2020 .
YU B , YIN H , ZHU Z . Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting [Z]. Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden; AAAIPress. 2018: 3634–40.
Lea C , Vidal R , Reiter A , et al . Temporal convolutional networks: A unified approach to action segmentation [C]// Computer vision–ECCV 2016 workshops: Amsterdam , the Netherlands, October 8-10 and 15 - 16 , 2016 , proceedings, part III 14 . Springer International Publishing, 2016: 47 - 54 .
Zhang S , Tong H , Xu J , et al . Graph convolutional networks: a comprehensive review [J]. Computational Social Networks , 2019 , 6 ( 1 ): 1 - 23 .
Song J , Son J , Seo D , et al . St-gat: A spatio-temporal graph attention network for accurate traffic speed prediction [C]// Proceedings of the 31st ACM international conference on information & knowledge management . 2022 : 4500 - 4504 .
Ho S L , Xie M . The use of ARIMA models for reliability forecasting and analysis [J]. Computers & industrial engineering , 1998 , 35 ( 1-2 ): 213 - 216 .
Min S , Gao Z , Peng J , et al . Stgsn—a spatial–temporal graph neural network framework for time-evolving social networks [J]. Knowledge-Based Systems , 2021 , 214 : 106746 .
Nargesian F , Samulowitz H , Khurana U , et al . Learning feature engineering for classification [C]// Ijcai . 2017 , 17 : 2529 - 2535 .
Jin M , Koh H Y , Wen Q , et al . A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024 .
Jiang L , Li X , Wu L , et al . Bearing fault diagnosis method based on a multi-head graph attention network [J]. Measurement Science and Technology , 2022 , 33 ( 7 ): 075012 .
Tampuu A , Matiisen T , Semikin M , et al . A survey of end-to-end driving: Architectures and training methods [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , 33 ( 4 ): 1364 - 1384 .
Richards J A . Analysis of periodically time-varying systems [M]. Springer Science & Business Media , 2012 .
Zhao H , Wang Y , Duan J , et al . Multivariate time-series anomaly detection via graph attention network [C]// 2020 IEEE international conference on data mining (ICDM) . IEEE , 2020 : 841 - 850 .
Wang J , Zhang S , Xiao Y , et al . A review on graph neural network methods in financial applications [J]. arXiv preprint arXiv: 2111.15367 , 2021 .
Wang Y , Jing C , Xu S , et al . Attention based spatiotemporal graph attention networks for traffic flow forecasting [J]. Information Sciences , 2022 , 607 : 869 - 883 .
Medsker L R , Jain L . Recurrent neural networks [J]. Design and Applications , 2001 , 5 ( 64-67 ): 2 .
Yu W , Kim I Y , Mechefske C . Analysis of different RNN autoencoder variants for time series classification and machine prognostics [J]. Mechanical Systems and Signal Processing , 2021 , 149 : 107322 .
Bai T , Zhang Y , Wu B , et al . Temporal graph neural networks for social recommendation [C]// 2020 IEEE International Conference on Big Data (Big Data) . IEEE , 2020 : 898 - 903 .
Li Y , Yu R , Shahabi C , et al . Diffusion convolutional recurrent neural network: Data-driven traffic forecasting [J]. International Conference on Learning Representations (ICLR) , 2018 .
Zhu J , Wang Q , Tao C , et al . AST-GCN: Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting [J]. Ieee Access , 2021 , 9 : 35973 - 35983 .
Kim H . Graph Transformer Networks [C]// Advances in Neural Information Processing Systems (NeurIPS) . Neural Information Processing Systems (NeurIPS) , 2019 .
Xing Y , He T , Xiao T , et al . Learning hierarchical graph neural networks for image clustering [C]// Proceedings of the IEEE/CVF international conference on computer vision . 2021 : 3467 - 3477 .
Xie Y , Xu Z , Zhang J , et al . Self-supervised learning of graph neural networks: A unified review [J]. IEEE transactions on pattern analysis and machine intelligence , 2022 , 45 ( 2 ): 2412 - 2429 .
Zhang H . Multivariate time series classification with graph neural networks [C]// Proceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms . 2024 : 361 - 367 .
Qin Y , Tao X , Fang Y , et al . DMGSTCN: Dynamic Multi-Graph Spatio-Temporal Convolution Network for Traffic Forecasting [J]. IEEE Internet of Things Journal , 2024 .
Han K , Koay A M Y , Ko R K L , et al . Adapting to the stream: an instance-attention GNN method for irregular multivariate time series data [J]. Frontiers of Computer Science , 2025 , 19 ( 8 ): 198340 .
Massobrio R , Nesmachnow S . Urban mobility data analysis for public transportation systems: a case study in Montevideo, Uruguay [J]. Applied Sciences , 2020 , 10 ( 16 ): 5400 .
Chen X , Boroujeni S P H , Shu X , et al . Enhancing Graph Neural Networks in Large-scale Traffic Incident Analysis with Concurrency Hypothesis [C]// Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems . 2024 : 196 - 207 .
Shi T , Xu H , Ma J , et al . ICU-TGNN: A Hybrid Multitask Transformer and Graph Neural Network Model for Predicting Clinical Outcomes of Patients in the ICU [C]// 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC) . IEEE , 2024 : 1761 - 1766 .
Luo Y , Liu Z , Wang L , et al . Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series [J]. Advances in Neural Information Processing Systems , 2024 , 37 : 67172 - 67199 .
Adi E , Anwar A , Baig Z , et al . Machine learning and data analytics for the IoT [J]. Neural computing and applications , 2020 , 32 : 16205 - 16233 .
Abid A , Khan M T , Iqbal J . A review on fault detection and diagnosis techniques: basics and beyond [J]. Artificial Intelligence Review , 2021 , 54 ( 5 ): 3639 - 3664 .
Ahanger A S , Khan S M , Masoodi F , et al . Advanced intrusion detection in internet of things using graph attention networks [J]. Scientific Reports , 2025 , 15 ( 1 ): 9831 .Bauwens L, Laurent S, Rombouts J V K. Multivariate GARCH models: a survey[J]. Journal of applied econometrics, 2006 , 21 ( 1 ): 79 - 109 .
Jin Y . GraphCNNpred: A stock market indices prediction using a Graph based deep learning system [C]// Proceedings of the 2024 2nd International Conference on Artificial Intelligence, Systems and Network Security . 2024 : 170 - 178 .
Kour V P , Arora S . Recent developments of the internet of things in agriculture: a survey [J]. Ieee Access , 2020 , 8 : 129924 - 129957 .
Fabricio M A , Behrens F H , Bianchini D . Monitoring of industrial electrical equipment using IoT [J]. IEEE Latin America Transactions , 2020 , 18 ( 08 ): 1425 - 1432 .
Zhao Z , Xiao Z , Tao J . MSDG: Multi-Scale Dynamic Graph Neural Network for Industrial Time Series Anomaly Detection [J]. Sensors , 2024 , 24 ( 22 ): 7218 .
Zhang F , Ding Y , Liao Y . Financial data collection based on big data intelligent processing [J]. International Journal of Information Technologies and Systems Approach (IJITSA) , 2023 , 16 ( 3 ): 1 - 13 .
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 .
Gonzalez J E , Xin R S , Dave A , et al . {GraphX}: Graph processing in a distributed dataflow framework [C]// 11th USENIX symposium on operating systems design and implementation (OSDI 14). 2014 : 599 - 613 .
Che Z , Purushotham S , Cho K , et al . Recurrent neural networks for multivariate time series with missing values [J]. Scientific reports , 2018 , 8 ( 1 ): 6085 .
Cao W , Wang D , Li J , et al . Brits: Bidirectional recurrent imputation for time series [J]. Advances in neural information processing systems , 2018 , 31 .
Luo D , Cheng W , Xu D , et al . Parameterized explainer for graph neural network [J]. Advances in neural information processing systems , 2020 , 33 : 19620 - 19631 .
Shanmugam K , Kocaoglu M , Dimakis A G , et al . Learning causal graphs with small interventions [J]. Advances in Neural Information Processing Systems , 2015 , 28 .
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 .
Pareja A , Domeniconi G , Chen J , et al . Evolvegcn: Evolving graph convolutional networks for dynamic graphs [C]// Proceedings of the AAAI conference on artificial intelligence . 2020 , 34 ( 04 ): 5363 - 5370 .
Sankar A , Wu Y , Gou L , et al . Dysat: Deep neural representation learning on dynamic graphs via self-attention networks [C]// Proceedings of the 13th international conference on web search and data mining . 2020 : 519 - 527 .
Gao P , Zhang H , Wang M , et al . Deep temporal graph infomax for imbalanced insider threat detection [J]. Journal of Computer Information Systems , 2025 , 65 ( 1 ): 108 - 118 .
You Y , Chen T , Sui Y , et al . Graph contrastive learning with augmentations [J]. Advances in neural information processing systems , 2020 , 33 : 5812 - 5823 .
Hassani K , Khasahmadi A H . Contrastive multi-view representation learning on graphs [C]// International conference on machine learning . PMLR , 2020 : 4116 - 4126 .
Zhang C , Xie Y , Bai H , et al . A survey on federated learning [J]. Knowledge-Based Systems , 2021 , 216 : 106775 .
Weiss K , Khoshgoftaar T M , Wang D D . A survey of transfer learning [J]. Journal of Big data , 2016 , 3 : 1 - 40 .
Farahani A , Voghoei S , Rasheed K , et al . A brief review of domain adaptation [J]. Advances in data science and information engineering: proceedings from ICDATA 2020 and IKE 2020 , 2021 : 877 - 894 .
Bi X , Jin Q , Song M , et al . Spatiotemporal Learning With Decoupled Causal Attention for Multivariate Time Series [J]. IEEE Transactions on Big Data , 2024 .
Xu Z , Liu Y , Wang Y , et al . Modeling Interactions Between Stocks Using LLM-Enhanced Graphs for Volume Prediction [C]// Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal) . 2025 : 153 - 163 .
Foumani N M , Miller L , Tan C W , et al . Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey [J]. ACM Computing Surveys , 2024 , 56 ( 9 ): 1 - 45 .
Fang Z , et al . A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification [J]. arXiv preprint arXiv: 2410.22377 , 2024 .
相关作者
相关机构
京公网安备11010802024621