|
|
|
Traffic flow prediction based on frequency-domain dynamic graph and Mamba |
| Yifei Zhang(张逸飞)1 and Jialin He(何嘉林)1,2,3,† |
1 School of Computer Science, China West Normal University, Nanchong 637009, China;
2 Artificial Intelligence Key Laboratory of Nanchong, China West Normal University, Nanchong 637009, China;
3 The Internet of Things Perception and Big Data Analysis Key Laboratory of Nanchong City, Nanchong 637009, China |
|
|
|
|
Abstract With the rapid advancement of intelligent transportation systems (ITS), urban traffic prediction faces significant challenges in effectively modeling complex spatio-temporal dynamics while maintaining computational efficiency. Existing approaches are often limited by static graph structures and the high computational cost of self-attention mechanisms when processing long sequences. To overcome these limitations, this paper proposes a novel framework, termed spatio-temporal frequency-domain mamba network (STFD-MambaNet). Specifically, the framework integrates a frequency-domain dynamic graph learner to capture evolving traffic topologies and employs the Mamba structured state space model to efficiently extract long-range temporal dependencies with linear complexity. Furthermore, a hierarchical spatial modeling module is developed to characterize multi-scale spatial correlations. Experiments conducted on four real-world datasets demonstrate that STFD-MambaNet consistently outperforms state-of-the-art methods in both accuracy and efficiency. The results further demonstrate the effective complementarity between frequency-domain dynamic graph learning and structured state space modeling, providing a robust solution for spatio-temporal traffic forecasting.
|
Received: 08 October 2025
Revised: 21 December 2025
Accepted manuscript online: 23 December 2025
|
|
PACS:
|
02.10.Ox
|
(Combinatorics; graph theory)
|
| |
45.70.Vn
|
(Granular models of complex systems; traffic flow)
|
| |
06.30.Ft
|
(Time and frequency)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant No. 62176217), the Program from the Sichuan Provincial Science and Technology, China (Grant No. 2018RZ0081), and the Fundamental Research Funds of China West Normal University (Grant No. 17E063). |
Corresponding Authors:
Jialin He
E-mail: hejialin32@126.com
|
Cite this article:
Yifei Zhang(张逸飞) and Jialin He(何嘉林) Traffic flow prediction based on frequency-domain dynamic graph and Mamba 2026 Chin. Phys. B 35 060204
|
[1] Jabbarpour M R, Zarrabi H and Khokhar R H 2018 Soft Comput. 22 2299
[2] Xu Y, Liu X, Cao X, et al. 2021 Innovation 2 4
[3] Lee C, Kim Y, Jin S, Kim D, Maciejewski R, Ebert D S and Ko S 2020 IEEE Trans. Vis. Comput. Graph. 26 3133
[4] Zhang J, Zheng Y, Qi D, Li R and Yi X 2016 Proc. ACM SIGSPATIAL Int. Conf. Adv. Geogr. Inf. Syst. 1
[5] Li Y and Shahabi C 2018 SIGSPATIAL Spec. 10 3
[6] Li Y, Yu R, Shahabi C and Liu Y 2017 arXiv:1707.01926 [cs.LG]
[7] Yu B, Yin H and Zhu Z 2018 IJCAI 3634
[8] Zhao L, Song Y, Zhang C, Liu Y, Wang P, Lin T, Deng M, Li Y and Li D 2019 IEEE Trans. Intell. Transp. Syst. 21 3848
[9] Li M and Zhu Z 2021 Proc. AAAI Conf. Artif. Intell. 35 4189
[10] Berndt D J and Clifford J 1994 Proc. KDD Workshop 10 359
[11] Zhang Y, Cao J, Wu Z, Xu H and Yu P S 2022 Proc. AAAI Conf. Artif. Intell. 36 2452
[12] Kusner M, Sun Y, Kolkin N and Weinberger K 2015 Proc. Int. Conf. Mach. Learn. 957
[13] van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A and Kavukcuoglu K 2016 arXiv:1609.03499 [cs.SD]
[14] Bai S, Kolter J Z and Koltun V 2018 arXiv:1803.01271 [cs.LG]
[15] Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H and Zhang W 2021 Proc. AAAI Conf. Artif. Intell. 35 11106
[16] Williams B M and Hoel L A 2003 J. Transp. Eng. 129 664
[17] Zivot E and Wang J 2006 Vector Autoregressive Models for Multivariate Time Series Modeling Financial Time Series with S-PLUS (New York: Springer) pp. 385
[18] van Lint J and van Hinsbergen C 2012 Artif. Intell. Appl. Crit. Transp. Issues 22 22
[19] Jeong Y S, Byon Y J, Castro-Neto M M and Easa S M 2013 IEEE Trans. Intell. Transp. Syst. 14 1700
[20] He K, Zhang X, Ren S and Sun J 2016 Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 770
[21] Yao H, Tang X, Wei H, Zheng G, Yu Y and Li Z 2018 arXiv:1803.01254 [cs.LG]
[22] Yao H, Wu F, Ke J, Tang X, Jia Y, Lu S, Gong P, Ye J and Li Z 2018 Proc. AAAI Conf. Artif. Intell. 2588
[23] Niepert M, Ahmed M and Kutzkov K 2016 Proc. Int. Conf. Mach. Learn. 2014
[24] Li C, Cui Z, Zheng W, Xu C and Yang J 2018 Proc. AAAI Conf. Artif. Intell. 3482
[25] Henaff M, Bruna J and LeCun Y 2015 arXiv:1506.05163 [cs.LG]
[26] Defferrard M, Bresson X and Vandergheynst P 2016 Adv. Neural Inf. Process. Syst. 29 3844
[27] Yu B, Yin H and Zhu Z 2018 Proc. Int. Joint Conf. Artif. Intell. 3634
[28] Gu A, Dao T, Li Z, Rudra A and Ré C 2023 Adv. Neural Inf. Process. Syst. 36 13759
[29] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser Ł and Polosukhin I 2017 Adv. Neural Inf. Process. Syst. 30 5998
[30] Shao Z, Zhang Z, Wei W, Wang F, Xu Y, Cao X, Zhang A and Xu C 2022 Proc. VLDB Endow. 15 2733
[31] Zhou H, Zhang S, Peng J, Zhang S, Li J, Xiong H and Zhang W 2021 Proc. AAAI Conf. Artif. Intell. 35 11106
[32] Liu S, Yu H, Liao C, Li J, Lin W and Liu A X 2021 Int. Conf. Learn. Represent.
[33] Zhou T, Ma Z, Wen Q, Wang X, Sun L and Jin R 2022 Proc. Int. Conf. Mach. Learn. 27268
[34] Wu H, Xu J, Wang J and Long M 2021 Adv. Neural Inf. Process. Syst. 34 22419
[35] Zheng C, Fan X, Wang C and Qi J 2020 Proc. AAAI Conf. Artif. Intell. 34 1234
[36] Liu H, Dong Z, Jiang R, Deng J, Jiang J, I N, Song X and Tsang I W 2023 Proc. ACM Int. Conf. Inf. Knowl. Manag. 4125
[37] Cui Y, Xie J and Zheng K 2021 Proc. ACM Int. Conf. Inf. Knowl. Manag. 2965
[38] Wu Z, Pan S, Long G, Jiang J and Zhang C 2019 Proc. Int. Joint Conf. Artif. Intell. 1907
[39] Li Y, Yu R, Shahabi C and Liu Y 2018 Int. Conf. Learn. Represent.
[40] Bai L, Yao L, Li C,Wang X andWang C 2020 Adv. Neural Inf. Process. Syst. 33 17804
[41] Wu Z, Pan S, Long G, Jiang J, Chang X and Zhang C 2020 Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 753
[42] Deng J, Chen X, Jiang R, Song X and Tsang I W 2021 Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 269 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
