计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (7): 205-212.doi: 10.11896/jsjkx.250600133

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

基于动态图卷积和超图学习的交通流量预测

赵星博1, 连德富2   

  1. 1 中国科学技术大学计算机学院 合肥 230000
    2 中国科学技术大学认知智能全国重点实验室 合肥 230000
  • 收稿日期:2025-06-20 修回日期:2025-08-11 出版日期:2026-07-15 发布日期:2026-07-10
  • 通讯作者: 连德富(liandefu@ustc.edu.cn)
  • 作者简介:(zhaoxingbo@mail.ustc.edu.cn)

Traffic Flow Forecasting Based on Dynamic Graph Convolution and Hypergraph Learning

ZHAO Xingbo1, LIAN Defu2   

  1. 1 School of Computer Science,University of Science and Technology of China,Hefei 230000,China
    2 State Key Laboratory of Cognitive Intelligence,University of Science and Technology of China,Hefei 230000,China
  • Received:2025-06-20 Revised:2025-08-11 Published:2026-07-15 Online:2026-07-10
  • About author:ZHAO Xingbo,born in 1999,postgra-duate.His main research interest is spatio-temporal data mining.
    LIAN Defu,born in 1985,professor,Ph.D supervisor.His main research interests include retrieval-augmented large models,large model agents,trustworthy artificial intelligence,recommender systems,and time-series large models.

PDF (PC)

24

摘要： 交通流量预测问题旨在基于历史观测数据实现未来交通状态的精准预测。为了更好地建模交通网络中的复杂时空关系,需要利用数据中存在的多种关联模式,包括成对关联和高阶关联。然而,在交通时空数据中关联模式是需要挖掘的,很难通过先验知识构建出有效的关联结构。对此,利用图结构来建模数据的成对关联,利用超图结构来建模数据的高阶关联,并通过注意力机制对图卷积和超图卷积进行自适应的动态整合。在成对关联建模中,利用节点嵌入来推断图结构。为了更好地捕捉数据中关联的动态变化特性,设计了一种动态图结构学习方法,从动态变化的数据中捕捉关联模式。在高阶关联建模中,利用矩阵优化来直接学习超图结构,并且为了有效地捕捉全局性依赖关系,引入了一个对比学习损失函数。在时间维度上,采用时序Transformer架构,利用自注意力机制实现交通流量时序依赖关系的多尺度建模。在多个常用的交通流量数据集上的实验表明,提出的模型能够很好地建模交通路网中的复杂时空关系,预测精度相较于多种基线模型有显著的提升。

关键词: 交通流量预测, 动态图卷积, 超图, 时空嵌入, 图神经网络

Abstract: The traffic flow prediction problem aims to accurately forecast future traffic conditions based on historical observation data.In order to better model the complex spatiotemporal relationships in the traffic network,it is essential to leverage various correlation patterns embedded in the data,including pairwise correlations and higher-order correlations.However,mining these correlation patterns from traffic spatiotemporal data poses significant challenges.Unlike many other domains where prior know-ledge can be used to construct effective correlation structures,traffic data often lacks clear predefined relationships.The dynamic nature of traffic networks further complicates the task,as correlation patterns can change over time due to factors such as weather conditions,accidents,or special events.Therefore,developing methods that can automatically discover and adapt to these changing patterns is crucial for improving the accuracy of traffic flow predictions.In this paper,a novel approach is proposed to address these challenges by utilizing both graph and hypergraph structures.In the pairwise correlation modeling,node embeddings are utilized to infer the graph structure.To better capture the dynamic changes in correlations within the data,a dynamic graph structure learning method is designed to capture correlation patterns from the dynamically changing data.In the higher-order correlation modeling,matrix optimization is employed to directly learn the hypergraph structure,and a contrastive learning loss function is introduced to effectively capture global dependencies.In the temporal dimension,a temporal Transformer architecture is adoptedto model the time-dependent aspects of traffic flow.The self-attention mechanism,a key component of the Transformer,is utilized to achieve multi-scale modeling of temporal dependencies.This allows the model to consider both short-term and long-term patterns in the data,which are essential for accurate traffic flow prediction.Experiments on multiple commonly used traffic flow datasets show that the proposed model can effectively model the complex spatiotemporal relationships in the traffic network,and its prediction accuracy is significantly improved compared to various baseline models.

Key words: Traffic flow forecasting, Dynamic graph convolution, Hypergraph, Spatio-temporal embedding, Graph neural network

中图分类号: 

  • TP183
[1]SIAMI-NAMINI S,TAVAKOLI N,NAMIN A S.A comparison of ARIMA and LSTM in forecasting time series[C]//2018 17th IEEE International Conference on Machine Learning and Applications(ICMLA).IEEE,2018:1394-1401.
[2]JIANG R,YIN D,WANG Z,et al.Dl-traff:Survey and benchmark of deep learning models for urban traffic prediction[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:4515-4525.
[3]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.
[4]TEDJOPURNOMO D A,BAO Z,ZHENG B,et al.A survey on modern deep neural network for traffic prediction:Trends,methods and challenges[J].IEEE Transactions on Knowledge and Data Engineering,2020,34(4):1544-1561.
[5]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.
[6]CUI Z,HENRICKSON K,KE R,et al.Traffic graph convolutional recurrent neural network:A deep learning framework for network-scale traffic learning and forecasting[J].IEEE Tran-sactions on Intelligent Transportation Systems,2019,21(11):4883-4894.
[7]ZHAO Z,CHEN W,WU X,et al.LSTM network:a deep learning approach for short-term traffic forecast[J].IET intelligent transport systems,2017,11(2):68-75.
[8]YU B,YIN H,ZHU Z.Spatio-temporal graph convolutional networks:A deep learning framework for traffic forecasting[J].arXiv:1709.04875,2017.
[9]LI Y,YU R,SHAHABI C,et al.Diffusion convolutional recurrent neural network:Data-driven traffic forecasting[J].arXiv:1707.01926,2017.
[10]WU Z,PAN S,LONG G,et al.Graph wavenet for deep spatial-temporal graph modeling[J].arXiv:1906.00121,2019.
[11]GUO S,LIN Y,FENG N,et al.Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:922-929.
[12]SONG C,LIN Y,GUO S,et al.Spatial-temporal synchronous graph convolutional networks:A new framework for spatial-temporal network data forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:914-921.
[13]WU Z,PAN S,LONG G,et al.Connecting the dots:Multivariate time series forecasting with graph neural networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:753-763.
[14]LAN S,MA Y,HUANG W,et al.Dstagnn:Dynamic spatial-temporal aware graph neural network for traffic flow forecasting[C]//International Conference on Machine Learning.PMLR,2022:11906-11917.
[15]BATTAGLIA P W,HAMRICK J B,BAPST V,et al.Relational inductive biases,deep learning,and graph networks[J].arXiv:1806.01261,2018.
[16]BRETTO A.Hypergraph theory[M].Cham:Springer,2013:209-216.
[17]YAN X,SONG T,JIAO Y,et al.Spatio-temporal hypergraph learning for next POI recommendation[C]//Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval.2023:403-412.
[18]ZHOU D,HUANG J,SCHÖLKOPF B.Learning with hypergraphs:Clustering,classification,and embedding[C]//Advances in Neural Information Processing Systems 19:Proceedings of the 2006 Conference.2006:1601-1608.
[19]FENG Y,YOU H,ZHANG Z,et al.Hypergraph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:3558-3565.
[20]ZHAO Y,LUO X,JU W,et al.Dynamic hypergraph structure learning for traffic flow forecasting[C]//2023 IEEE 39th International Conference on Data Engineering(ICDE).IEEE,2023:2303-2316.
[21]YADATI N,NIMISHAKAVI M,YADAV P,et al.Hypergcn:A new method for training graph convolutional networks on hypergraphs[C]//NeurIPS 2019.2019.
[22]JIANG J,WEI Y,FENG Y,et al.Dynamic hypergraph neural networks[C]//IJCAI.2019:2635-2641.
[23]CAO D,WANG Y,DUAN J,et al.Spectral temporal graph neural network for multivariate time-series forecasting[J].Advances in Neural Information Processing Systems,2020,33:17766-17778.
[24]LU B,GAN X,JIN H,et al.Spatiotemporal adaptive gatedgraph convolution network for urban traffic flow forecasting[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management.2020:1025-1034.
[25]DIAO Z,WANG X,ZHANG D,et al.Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:890-897.
[26]GUO K,HU Y,SUN Y,et al.Hierarchical graph convolutionnetwork for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:151-159.
[27]LI M,ZHU Z.Spatial-temporal fusion graph neural networksfor traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4189-4196.
[28]CIRSTEA R G,YANG B,GUO C,et al.Towards spatio-temporal aware traffic time series forecasting[C]//2022 IEEE 38th International Conference on Data Engineering(ICDE).IEEE,2022:2900-2913.
[29]SHAO Z,ZHANG Z,WANG F,et al.Spatial-temporal identity:A simple yet effective baseline for multivariate time series forecasting[C]//Proceedings of the 31st ACM International Confe-rence on Information & Knowledge Management.2022:4454-4458.
[30]SHAO Z,ZHANG Z,WEI W,et al.Decoupled dynamic spatial-temporal graph neural network for traffic forecasting[J].arXiv:2206.09112,2022.
[31]BAI L,YAO L,LI C,et al.Adaptive graph convolutional recurrent network for traffic forecasting[J].Advances in neural information processing systems,2020,33:17804-17815.
[32]LI Z,HUANG C,XIA L,et al.Spatial-temporal hypergraphself-supervised learning for crime prediction[C]//2022 IEEE 38th International Conference on Data Engineering(ICDE).IEEE,2022:2984-2996.
[33]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[34]XU M,DAI W,LIU C,et al.Spatial-temporal transformer networks for traffic flow forecasting[J].arXiv:2001.02908,2020.
[35]ZENG A,CHEN M,ZHANG L,et al.Are transformers effective for time series forecasting?[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2023:11121-11128.
[36]ZHOU H,ZHANG S,PENG J,et al.Informer:Beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:11106-11115.
[37]ZHOU T,MA Z,WEN Q,et al.Fedformer:Frequency enhanced decomposed transformer for long-term series forecasting[C]//International Conference on Machine Learning.PMLR,2022:27268-27286.
[38]ZHENG C,FAN X,WANG C,et al.Gman:A graph multi-at-tention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:1234-1241.
[39]JIANG J,HAN C,ZHAO W X,et al.Pdformer:Propagation delay-aware dynamic long-range transformer for traffic flow prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2023:4365-4373.
[40]SUN Y,JIANG X,HU Y,et al.Dual dynamic spatial-temporal graph convolution network for traffic prediction[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(12):23680-23693.
[41]HUANG Y,XIAO N.Self-Supervised Masked Hypergraph Autoencoders for Spatio-Temporal Forecasting[C]//2024 International Joint Conference on Neural Networks(IJCNN).IEEE,2024:1-8.
[42]LONG B,ZHU W,XIAO J.ST-RetNet:A Long-Term Spatial-Temporal Traffic Flow Prediction Method[C]//Chinese Confe-rence on Pattern Recognition and Computer Vision(PRCV).Singapore:Springer Nature Singapore,2024:3-16.
[43]WANG S C,TANG Y.Auto-correlation Attention and Dynami-cs Convolution Based Spatial-temporal Networks for Traffic Forecasting[J].Journal of Chinese Computer Systems,2024,45(6):1418-1425.
[44]ZAHO W Z,YUAN G,ZHANG Y M,et al.Multi-view Fused Spatial-temporal Dynamic GCN for Urban Traffic Flow Prediction[J].Ruan Jian Xue Bao/Journal of Software,2024,35(4):1751-1773.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发