Online transfer learning with an MLP-assisted graph convolutional network for traffic flow prediction: a solution for edge intelligent devices

Jingru SUN; Chendingying LU; Yichuang SUN; Hongbo JIANG; Zhu XIAO

doi:10.1631/FITEE.2401059

Your Location：

Home >

Browse articles >

Online transfer learning with an MLP-assisted graph convolutional network for traffic flow prediction: a solution for edge intelligent devices

Regular Papers | Updated：2025-11-05

- Online transfer learning with an MLP-assisted graph convolutional network for traffic flow prediction: a solution for edge intelligent devices
- 在线迁移学习与多层感知机辅助图卷积网络用于交通流预测：面向边缘智能设备的解决方案
- Frontiers of Information Technology & Electronic Engineering Vol. 26, Issue 9, Pages: 1692-1710(2025)
- Affiliations：
  
  1.College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
  2.Chongqing Research Institute, Hunan University, Chongqing 401120, China
  3.School of Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UK
- Author bio：
  
  ‡ Corresponding author
- Funds：
- DOI：10.1631/FITEE.2401059
  CLC： U491.1;TP18
- Received：12 December 2024，
  
  Revised：2025-03-02，
  
  Published：2025-09
- Accepted：
Scan QR Code
Jingru SUN, Chendingying LU, Yichuang SUN, et al. Online transfer learning with an MLP-assisted graph convolutional network for traffic flow prediction: a solution for edge intelligent devices[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(9): 1692-1710.
DOI：

Jingru SUN, Chendingying LU, Yichuang SUN, et al. Online transfer learning with an MLP-assisted graph convolutional network for traffic flow prediction: a solution for edge intelligent devices[J]. Frontiers of Information Technology & Electronic Engineering, 2025, 26(9): 1692-1710. DOI： 10.1631/FITEE.2401059.

摘要

交通流预测对于智能交通系统至关重要，并有助于路线规划和导航。然而，现有研究通常侧重于提高预测准确性，而忽视了外部影响和边缘设备的实际问题，如资源限制和数据稀疏性。本文提出一种基于在线迁移学习和多层感知机辅助图卷积网络的框架（OTL-GM），该框架由两部分组成：将源领域特征转移到边缘设备，并通过在线学习弥合领域间的差距。在4个数据集上验证了在线迁移学习的有效性；与未采用在线迁移学习的模型相比，采用在线迁移学习模型时，不同模型收敛时间减少的比例从24.77%到95.32%不等。

Abstract

Traffic flow prediction is crucial for intelligent transportation and aids in route planning and navigation. However

existing studies often focus on prediction accuracy improvement

while neglecting external influences and practical issues like resource constraints and data sparsity on edge devices. We propose an online transfer learning (OTL) framework with a multi-layer perceptron (MLP)-assisted graph convolutional network (GCN)

termed OTL-GM

which consists of two parts: transferring source-domain features to edge devices and using online learning to bridge domain gaps. Experiments on four data sets demonstrate OTL's effectiveness; in a comparison with models not using OTL

the reduction in the convergence time of the OTL models ranges from 24.77% to 95.32%.

关键词

Keywords

references

Asim M , Wang Y , Wang KZ , et al. , 2020 . A review on computational intelligence techniques in cloud and edge computing . IEEE Trans Emerg Top Comput Intell , 4 ( 6 ): 742 - 763 . https://doi.org/10.1109/TETCI.2020.3007905 https://doi.org/10.1109/TETCI.2020.3007905

Bai L , Yao LN , Li C , et al. , 2020 . Adaptive graph convolutional recurrent network for traffic forecasting . Proc 34 th Annual Conf on Neural Information Processing Systems , Article 1494 .

Bando M , Hasebe K , Nakayama A , et al. , 1995 . Dynamical model of traffic congestion and numerical simulation . Phys Rev E , 51 ( 2 ): 1035 - 1042 . https://doi.org/10.1103/PhysRevE.51.1035 https://doi.org/10.1103/PhysRevE.51.1035

Bojan TM , Kumar UR , Bojan VM , 2014 . An Internet of Things based intelligent transportation system . Proc IEEE Int Conf on Vehicular Electronics and Safety , p. 174 - 179 . https://doi.org/10.1109/ICVES.2014.7063743 https://doi.org/10.1109/ICVES.2014.7063743

Bruna J , Zaremba W , Szlam A , et al. , 2014 . Spectral networks and locally connected networks on graphs . Proc 2 nd Int Conf on Learning Representations , p. 1 - 14 .

Chen C , Li KL , Teo SG , et al. , 2020 . Citywide traffic flow prediction based on multiple gated spatio-temporal convolutional neural networks . ACM Trans Knowl Discov Data , 14 ( 4 ): 42 . https://doi.org/10.1145/3385414 https://doi.org/10.1145/3385414

Cong PJ , Zhou JL , Li LY , et al. , 2021 . A survey of hierarchical energy optimization for mobile edge computing: a perspective from end devices to the cloud . ACM Comput Surv , 53 ( 2 ): 38 . https://doi.org/10.1145/3378935 https://doi.org/10.1145/3378935

Crammer K , Dekel O , Keshet J , et al. , 2006 . Online passive-aggressive algorithms . J Mach Learn Res , 7 ( 3 ): 515 - 585 .

Datla S , Sharma S , 2008 . Impact of cold and snow on temporal and spatial variations of highway traffic volumes . J Transp Geogr , 16 ( 5 ): 358 - 372 . https://doi.org/10.1016/j.jtrangeo.2007.12.003 https://doi.org/10.1016/j.jtrangeo.2007.12.003

Defferrard M , Bresson X , Vandergheynst P , 2016 . Convolutional neural networks on graphs with fast localized spectral filtering . Proc 30 th Int Conf on Neural Information Processing Systems , p. 3844 - 3852 .

Derawi M , Dalveren Y , Cheikh FA , 2020 . Internet-of-Things-based smart transportation systems for safer roads . Proc 6 th World Forum on Internet of Things , p. 1 - 4 . https://doi.org/10.1109/WF-IoT48130.2020.9221208 https://doi.org/10.1109/WF-IoT48130.2020.9221208

Diao ZL , Wang X , Zhang DF , et al. , 2019 . Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting . Proc 33 rd AAAI Conf on Artificial Intelligence , p. 890 - 897 .

Gentile C , 2000 . A new approximate maximal margin classification algorithm . Proc 14 th Int Conf on Neural Information Processing Systems , p. 479 - 485 .

Gräber T , Lupberger S , Unterreiner M , et al. , 2019 . A hybrid approach to side-slip angle estimation with recurrent neural networks and kinematic vehicle models . IEEE Trans Intell Veh , 4 ( 1 ): 39 - 47 . https://doi.org/10.1109/TIV.2018.2886687 https://doi.org/10.1109/TIV.2018.2886687

Guo G , Yuan W , Liu JY , et al. , 2023 . Traffic forecasting via dilated temporal convolution with peak-sensitive loss . IEEE Intell Transp Syst Mag , 15 ( 1 ): 48 - 57 . https://doi.org/10.1109/MITS.2021.3119869 https://doi.org/10.1109/MITS.2021.3119869

Guo SN , Lin YF , Wan HY , et al. , 2022 . Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting . IEEE Trans Knowl Data Eng , 34 ( 11 ): 5415 - 5428 . https://doi.org/10.1109/TKDE.2021.3056502 https://doi.org/10.1109/TKDE.2021.3056502

Hamed MM , Al-Masaeid HR , Said ZMB , 1995 . Short-term prediction of traffic volume in urban arterials . J Transp Eng , 121 ( 3 ): 249 - 254 . https://doi.org/10.1061/(ASCE)0733-947X(1995)121:3(249) https://doi.org/10.1061/(ASCE)0733-947X(1995)121:3(249)

Han PC , Wang SQ , Leung KK , 2020 . Adaptive gradient sparsification for efficient federated learning: an online learning approach . Proc 40 th Int Conf on Distributed Computing Systems , p. 300 - 310 . https://doi.org/10.1109/ICDCS47774.2020.00026 https://doi.org/10.1109/ICDCS47774.2020.00026

Hashemi H , Abdelghany K , 2015 . Real-time traffic network state prediction for proactive traffic management: simulation experiments and sensitivity analysis . Transp Res Rec , 2491 ( 1 ): 22 - 31 . https://doi.org/10.3141/2491-03 https://doi.org/10.3141/2491-03

Jeong YS , Byon YJ , Castro-Neto MM , et al. , 2013 . Supervised weighting-online learning algorithm for short-term traffic flow prediction . IEEE Trans Intell Transp Syst , 14 ( 4 ): 1700 - 1707 . https://doi.org/10.1109/TITS.2013.2267735 https://doi.org/10.1109/TITS.2013.2267735

Jia YH , Wu JP , Du YM , 2016 . Traffic speed prediction using deep learning method . Proc 19 th Int Conf on Intelligent Transportation Systems , p. 1217 - 1222 . https://doi.org/10.1109/ITSC.2016.7795712 https://doi.org/10.1109/ITSC.2016.7795712

Kashyap AA , Raviraj S , Devarakonda A , et al. , 2022 . Traffic flow prediction models—a review of deep learning techniques . Cog Eng , 9 ( 1 ): 2010510 . https://doi.org/10.1080/23311916.2021.2010510 https://doi.org/10.1080/23311916.2021.2010510

Kipf TN , Welling M , 2017 . Semi-supervised classification with graph convolutional networks . Proc 5 th Int Conf on Learning Representations .

Krizhevsky A , Sutskever I , Hinton GE , 2017 . ImageNet classification with deep convolutional neural networks . Commun ACM , 60 ( 6 ): 84 - 90 . https://doi.org/10.1145/3065386 https://doi.org/10.1145/3065386

Kwon YD , Chauhan J , Mascolo C , 2021 . FastICARL: fast incremental classifier and representation learning with efficient budget allocation in audio sensing applications . Proc 22 nd Annual Conf of the International Speech Communication Association , p. 356 - 360 .

Lee M , Choi YY , Park SW , et al. , 2024 . A gated MLP architecture for learning topological dependencies in spatio-temporal graphs . https://arxiv.org/html/2401.15894v1 https://arxiv.org/html/2401.15894v1

Li Y , Long PM , 1999 . The relaxed online maximum margin algorithm . Proc 13 th Int Conf on Neural Information Processing Systems , p. 361 - 387 .

Li YG , Yu R , Shahabi C , et al. , 2018 . Diffusion convolutional recurrent neural network: data-driven traffic forecasting . Proc 6 th Int Conf on Learning Representations .

Liu HC , Dong Z , Jiang RH , et al. , 2023 . Spatio-temporal adaptive embedding makes vanilla Transformer SOTA for traffic forecasting . Proc 32 nd ACM Int Conf on Information and Knowledge Management , p. 4125 - 4129 .

Liu J , Guan W , 2004 . A summary of traffic flow forecasting methods . J High Transp Res Dev , 21 ( 3 ): 82 - 85 (in Chinese) . https://doi.org/10.3969/j.issn.1002-0268.2004.03.022 https://doi.org/10.3969/j.issn.1002-0268.2004.03.022

Lu B , Gan XY , Zhang WN , et al. , 2022 . Spatio-temporal graph few-shot learning with cross-city knowledge transfer . Proc 28 th ACM SIGKDD Conf on Knowledge Discovery and Data Mining , p. 1162 - 1172 . https://doi.org/10.1145/3534678.3539281 https://doi.org/10.1145/3534678.3539281

Lv YS , Duan YJ , Kang WW , et al. , 2014 . Traffic flow prediction with big data: a deep learning approach . IEEE Trans Int Transp Syst , 16 ( 2 ): 865 - 873 . https://doi.org/10.1109/TITS.2014.2345663 https://doi.org/10.1109/TITS.2014.2345663

Mallick T , Balaprakash P , Rask E , et al. , 2021 . Transfer learning with graph neural networks for short-term highway traffic forecasting . Proc 25 th Int Conf on Pattern Recognition , p. 10367 - 10374 . https://doi.org/10.1109/ICPR48806.2021.9413270 https://doi.org/10.1109/ICPR48806.2021.9413270

Nellore K , Hancke GP , 2016 . A survey on urban traffic management system using wireless sensor networks . Sensors , 16 ( 2 ): 157 . https://doi.org/10.3390/s16020157 https://doi.org/10.3390/s16020157

Qadri YA , Nauman A , Zikria YB , et al. , 2020 . The future of healthcare Internet of Things: a survey of emerging technologies . IEEE Commun Surv Tut , 22 ( 2 ): 1121 - 1167 . https://doi.org/10.1109/COMST.2020.2973314 https://doi.org/10.1109/COMST.2020.2973314

Rosenblatt F , 1958 . The perceptron: a probabilistic model for information storage and organization in the brain . Psychol Rev , 65 ( 6 ): 386 - 408 . https://doi.org/10.1037/h0042519 https://doi.org/10.1037/h0042519

Rumelhart DE , Hinton GE , Williams RJ , 1986 . Learning representations by back-propagating errors . Nature , 323 ( 6088 ): 533 - 536 . https://doi.org/10.1038/323533a0 https://doi.org/10.1038/323533a0

Singh R , Sharma R , Akram SV , et al. , 2021 . Highway 4.0: digitalization of highways for vulnerable road safety development with intelligent IoT sensors and machine learning . Saf Sci , 143 : 105407 . https://doi.org/10.1016/j.ssci.2021.105407 https://doi.org/10.1016/j.ssci.2021.105407

Sun JR , Peng M , Jiang HB , et al. , 2022 . HMIAN: a hierarchical mapping and interactive attention data fusion network for traffic forecasting . IEEE Int Things J , 9 ( 24 ): 25685 - 25697 . https://doi.org/10.1109/JIOT.2022.3196461 https://doi.org/10.1109/JIOT.2022.3196461

Sutskever I , Vinyals O , Le QV , 2014 . Sequence to sequence learning with neural networks . Proc 28 th Int Conf on Neural Information Processing Systems , p. 3104 - 3112 .

Tang C , Sun JR , Sun YC , et al. , 2020 . A general traffic flow prediction approach based on spatial-temporal graph attention . IEEE Access , 8 : 153731 - 153741 . https://doi.org/10.1109/ACCESS.2020.3018452 https://doi.org/10.1109/ACCESS.2020.3018452

Tzeng E , Hoffman J , Darrell T , et al. , 2015 . Simultaneous deep transfer across domains and tasks . Proc IEEE Int Conf on Computer Vision , p. 4068 - 4076 .

van Lint H , van Hinsbergen C , 2012 . Short-term traffic and travel time prediction models . Artif Intell Appl Crit Transp Iss , 22 ( E-C168 ): 22 - 41 .

Vaswani A , Shazeer N , Parmar N , et al. , 2017 . Attention is all you need . Proc 31 st Int Conf on Neural Information Processing Systems , p. 6000 - 6010 .

Wang SZ , Miao H , Li JY , et al. , 2022 . Spatio-temporal knowledge transfer for urban crowd flow prediction via deep attentive adaptation networks . IEEE Trans Intell Transp Syst , 23 ( 5 ): 4695 - 4705 . https://doi.org/10.1109/TITS.2021.3055207 https://doi.org/10.1109/TITS.2021.3055207

Williams BM , Hoel LA , 2003 . Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results . J Transp Eng , 129 ( 6 ): 664 - 672 . https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664) https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)

Yao ZX , Xia SC , Li Y , et al. , 2023 . Transfer learning with spatial-temporal graph convolutional network for traffic prediction . IEEE Trans Intell Transp Syst , 24 ( 8 ): 8592 - 8605 . https://doi.org/10.1109/TITS.2023.3250424 https://doi.org/10.1109/TITS.2023.3250424

Yu B , Yin HT , Zhu ZX , 2017 . Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting . Proc 27 th Int Joint Conf on Artificial Intelligence , p. 3634 - 3640 .

Zhang CY , Patras P , 2018 . Long-term mobile traffic forecasting using deep spatio-temporal neural networks . Proc 18 th ACM Int Symp on Mobile Ad Hoc Networking and Computing , p. 231 - 240 . https://doi.org/10.1145/3209582.3209606 https://doi.org/10.1145/3209582.3209606

Zhang H , Lu XX , 2020 . Vehicle communication network in intelligent transportation system based on Internet of Things . Comput Commun , 160 : 799 - 806 . https://doi.org/10.1016/j.comcom.2020.03.041 https://doi.org/10.1016/j.comcom.2020.03.041

Zhang T , Guo G , 2022 . Graph attention LSTM: a spatiotemporal approach for traffic flow forecasting . IEEE Intell Transp Syst Mag , 14 ( 2 ): 190 - 196 . https://doi.org/10.1109/MITS.2020.2990165 https://doi.org/10.1109/MITS.2020.2990165

Zhao L , Song YJ , Zhang C , et al. , 2020 . T-GCN: a temporal graph convolutional network for traffic prediction . IEEE Trans Intell Transp Syst , 21 ( 9 ): 3848 - 3858 . https://doi.org/10.1109/TITS.2019.2935152 https://doi.org/10.1109/TITS.2019.2935152

Zhao PL , Hoi SCH , Jin R , 2011 . Double updating online learning . J Mach Learn Res , 12 : 1587 - 1615 .

Zhu JW , Wang QJ , Tao C , et al. , 2021 . AST-GCN: attribute-augmented spatiotemporal graph convolutional network for traffic forecasting . IEEE Access , 9 : 35973 - 35983 . https://doi.org/10.1109/ACCESS.2021.3062114 https://doi.org/10.1109/ACCESS.2021.3062114

Zivot E , Wang JH , 2006 . Vector autoregressive models for multivariate time series . In: Modeling Financial Time Series with S-PLUS . Springer , New York , p. 385 - 429 . https://doi.org/10.1007/978-0-387-32348-0_11 https://doi.org/10.1007/978-0-387-32348-0_11

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Map

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰