Spatial-Temporal Traffic Data Imputation Method with Uncertainty Modeling

Liu Le; Guo Shengnan; Jin Xiyuan; Zhao Miaomiao; Chen Ran; Lin Youfang; Wan Huaiyu

doi:10.7544/issn1000-1239.202330455

Journal of Computer Research and Development > 2025 > 62(2): 346-363. > DOI: 10.7544/issn1000-1239.202330455 CSTR: 32373.14.issn1000-1239.202330455

Liu Le, Guo Shengnan, Jin Xiyuan, Zhao Miaomiao, Chen Ran, Lin Youfang, Wan Huaiyu. Spatial-Temporal Traffic Data Imputation Method with Uncertainty Modeling[J]. Journal of Computer Research and Development, 2025, 62(2): 346-363. DOI: 10.7544/issn1000-1239.202330455

Citation:

PDF (1673 KB)

Spatial-Temporal Traffic Data Imputation Method with Uncertainty Modeling

Liu Le^{1, 2,},
Guo Shengnan^{1, 2, ,},
Jin Xiyuan^{1, 2},
Zhao Miaomiao¹,
Chen Ran¹,
Lin Youfang^{1, 2},
Wan Huaiyu^{1, 2}

1.
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044
2.
Beijing Key Laboratory of Traffic Data Analysis and Mining (Beijing Jiaotong University), Beijing 100044

Funds: This work was supported by the National Natural Science Foundation of China for Young Scientists (62202043).

More Information

Author Bio:
Liu Le: born in 1999. Master. His main research interests include spatial-temporal data mining and deep learning

Guo Shengnan: born in 1992. PhD, lecturer. Member of CCF. Her main research interests include spatial-temporal data mining and deep learning

Jin Xiyuan: born in 1997. PhD candidate. Student member of CCF. His main research interests include spatial-temporal data mining and uncertainty estimation

Zhao Miaomiao: born in 2002. Undergraduate. Her main research interest includes spatial-temporal data mining

Chen Ran: born in 2002. Undergraduate. Her main research interest includes spatial-temporal data imputation

Lin Youfang: born in 1971. PhD, professor. Senior member of CCF. His main research interests include data mining, machine learning, reinforcement learning, complex network, and intelligent technology and system

Wan Huaiyu: born in 1981. PhD, professor. Member of CCF. His main research interests include spatial-temporal data mining, information extraction、social networks mining
Received Date: June 04, 2023
Revised Date: January 10, 2024
Accepted Date: March 05, 2024
Available Online: March 06, 2024

Graphical Abstract

Abstract

Abstract

Traffic data missing is one of the unavoidable problems in intelligent transportation systems. Completing and quantifying the uncertainty of missing values can improve the performance and reliability of traffic data mining tasks in intelligent transportation systems. However, most existing traffic data imputation models mainly focus on point estimation without quantifying the uncertainty, so they cannot meet the need for traffic data reliability in the transportation field. Besides, these methods only focus on modeling spatial-temporal correlation of traffic data, failing to consider the impact of missing values on spatial-temporal correlation. In addition, the uncertainty of traffic data is affected by time, spatial location, and the state of the data, but existing methods cannot comprehensively consider these factors. To address these challenges, we propose a spatial-temporal uncertainty guided traffic data imputation network (STUIN), which simultaneously realizes the imputation of spatial-temporal traffic data and the uncertainty quantification of the imputation results by self-supervised training. Specifically, we innovatively model the hidden states of the neural network as random variables subject to Gaussian distributions, use the variances of Gaussian distributions to model the uncertainty of the hidden states, and introduce a variance-based attention mechanism to characterize the effect of uncertainty on modeling spatio-temporal correlations. In addition, we design a novel spatial-temporal uncertainty initialization module, which incorporates the influence of time, space and missing values when initializing the means and variances of the Gaussian distributions. Experiments on two traffic flow datasets show that STUIN achieves state-of-the-art performance on both the data imputation and uncertainty quantification tasks.

FullText(HTML)

References (33)

References

[1]	Qu Li, Li Li, Zhang Yi, et al. PPCA-based missing data imputation for traffic flow volume: A systematical approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3): 512−522 doi: 10.1109/TITS.2009.2026312
[2]	Abdar M, Pourpanah F, Hussain S, et al. A review of uncertainty quantification in deep learning: Techniques, applications and challenges[J]. Information Fusion, 2021, 76: 243-297 Abdar M,Pourpanah F,Hussain S,et al. A review of uncertainty quantification in deep learning:Techniques,applications and challenges[J]. Information Fusion,2021,76:243-297
[3]	Guo Shengnan, Lin Youfang, Wan Huaiyu, et al. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(11): 5415−5428 doi: 10.1109/TKDE.2021.3056502
[4]	Guo Shengnan, Lin Youfang, Feng Ning, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proc of the 33rd AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2019: 922−929
[5]	Yuan Haitao, Li Guoliang. A survey of traffic prediction: From spatio-temporal data to intelligent transportation[J]. Data Science and Engineering, 2021, 6: 63−85 Yuan Haitao,Li Guoliang. A survey of traffic prediction:From spatio-temporal data to intelligent transportation[J]. Data Science and Engineering,2021,6:63−85
[6]	倪庆剑,彭文强,张志政,等. 基于信息增强传输的时空图神经网络交通流预测[J]. 计算机研究与发展,2022,59(2):282−293 doi: 10.7544/issn1000-1239.20210901 Ni Qingjian, Peng Wenqiang, Zhang Zhizheng, et al. Spatial-temporal graph neural network for traffic flow prediction based on information enhanced transmission[J]. Journal of Computer Research and Development, 2022, 59(2): 282−293 (in Chinese) doi: 10.7544/issn1000-1239.20210901
[7]	Lebel J M, Kratz F, Bloch G. Missing values rebuilding by prediction and ARIMA modelling in time series[J]. Advanced Information Processing in Automatic Control, 1989, 22(6): 357−361
[8]	Hudak A T, Crookston N L, Evans J S, et al. Nearest neighbor imputation of species-level, plot-scale forest structure attributes from lidar data[J]. Remote Sensing of Environment, 2008, 112(5): 2232−2245 doi: 10.1016/j.rse.2007.10.009
[9]	Chen Xinyu, Lei Mengying, Saunier N, et al. Low-rank autoregressive tensor completion for spatiotemporal traffic data imputation[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(8): 12301−12310 doi: 10.1109/TITS.2021.3113608
[10]	Mattei P A, Frellsen J. MIWAE: Deep generative modelling and imputation of incomplete data sets[C]//Proc of the 36th Int Conf on Machine Learning. New York: ACM, 2019: 4413−4423
[11]	Che Zhengping, Purushotham S, Cho K, et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8(1): 6085−6099 doi: 10.1038/s41598-018-24271-9
[12]	Cao Wei, Wang Dong, Li Jian, et al. BRITS: Bidirectional recurrent imputation for time series[C]//Proc of the 32nd Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2018: 6776−6786
[13]	Shukla S N, Marlin B M. Multi-time attention networks for irregularly sampled time series[C/OL]//Proc of the 9th Int Conf on Learning Representations. San Juan, CA: ICLR, 2021[2021-11-21]. https://openreview.net/forum?id=mXbhcalKnYM
[14]	Wu Yuankai, Zhuang Dingyi, Labbe A, et al. Inductive graph neural networks for spatiotemporal Kriging[C]//Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 4478−4485
[15]	Li Yaguang, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting[C/OL]//Proc of the 6th Int Conf on Learning Representations. San Juan, CA: ICLR, 2018[2021-08-04]. https://openreview.net/forum?id=SJiHXGWAZ
[16]	Xu Dongwei, Peng Hang, Wei Chenchen, et al. Traffic state data imputation: An efficient generating method based on the graph aggregator[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(8): 13084−13093
[17]	Hamilton W, Ying Zhitao, Leskovec J. Inductive representation learning on large graphs[C]//Proc of the 31st Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 1024−1034
[18]	Ye Yongchao, Zhang Shiyao, Yu J J Q. Spatial-temporal traffic data imputation via graph attention convolutional network[C]//Proc of the 30th Int Conf on Artificial Neural Networks. Berlin: Springer, 2021: 241−252
[19]	Blundell C, Cornebise J, Kavukcuoglu K, et al. Weight uncertainty in neural networks[C]//Proc of the 32nd Int Conf on Machine Learning. New York: ACM, 2015: 1613−1622
[20]	Louizos C, Welling M. Multiplicative normalizing flows for variational Bayesian neural networks[C]//Proc of the 34th Int Conf on Machine Learning. New York: ACM, 2017: 2218–2227
[21]	Wu Anqi, Nowozin S, Meeds E, et al. Deterministic variational inference for robust Bayesian neural networks[C/OL]//Proc of the 7th Int Conf on Learning Representations. San Juan, CA: ICLR, 2019[2022-03-14]. https://openreview.net/forum?id=B1l08oAct7
[22]	Welling M, Teh Y W. Bayesian learning via stochastic gradient Langevin dynamics[C]//Proc of the 28th Int Conf on Machine Learning. New York: ACM, 2011: 681−688
[23]	Li Chunyuan, Chen Changyou, Carlson D E, et al. Preconditioned stochastic gradient Langevin dynamics for deep neural networks[C]//Proc of the 30th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2016: 1788−1794
[24]	Gal Y, Ghahramani Z. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning[C]//Proc of the 33rd Int Conf on Machine Learning. New York: ACM, 2016: 1050−1059
[25]	Gal Y, Ghahramani Z. A theoretically grounded application of dropout in recurrent neural networks[C]//Proc of the 30th Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2016: 1027–1035
[26]	Wu Dongxia, Gao Liyao, Chinazzi M, et al. Quantifying uncertainty in deep spatial-temporal forecasting[C]//Proc of the 27th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2021: 1841−1851
[27]	Koenker R, Hallock K. Quantile regression[J]. Journal of Economic Perspectives, 2001, 15(4): 143−156 doi: 10.1257/jep.15.4.143
[28]	Gasthaus J, Benidis K, Wang Yuyang, et al. Probabilistic forecasting with spline quantile function RNNs[C]//Proc of the 22nd Int Conf on Artificial Intelligence and Statistics. Cambridge, MA: JMLR, 2019: 1901−1910
[29]	Salinas D, Flunkert V, Gasthaus J, et al. DeepAR: Probabilistic forecasting with autoregressive recurrent networks[J]. International Journal of Forecasting, 2020, 36(3): 1181−1191 doi: 10.1016/j.ijforecast.2019.07.001
[30]	Zhou Zhengyang, Wang Yang, Xie Xike, et al. STUaNet: Understanding uncertainty in spatiotemporal collective human mobility[C]//Proc of the 30th Int World Wide Web Conf. Berlin: Springer, 2021: 1868−1879
[31]	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 31st Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2017: 6000–6010
[32]	Tashiro Y, Song Jiaming, Song Yang, et al. CSDI: Conditional score-based diffusion models for probabilistic time series imputation[C]//Proc of the 35th Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2021: 24804−24816
[33]	Bai Lei, Yao Lina, Li Can, et al. Adaptive graph convolutional recurrent network for traffic forecasting[C]//Proc of the 34th Conf on Neural Information Processing Systems. Cambridge, MA: MIT, 2020: 17804−17815

[1]	Xie Wenbing, Guan Ruixue, Zhang Yiming, Li Jiamei, Wang Jun. Efficient Optimization of Erasure Coding for Storage Library[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202440091
[2]	Yan Zhiyuan, Xie Biwei, Bao Yungang. HVMS: A Hybrid Vectorization-Optimized Mechanism of SpMV[J]. Journal of Computer Research and Development, 2024, 61(12): 2969-2984. DOI: 10.7544/issn1000-1239.202330204
[3]	Wang Chuang, Ding Yan, Huang Chenlin, Song Liantao. Bitsliced Optimization of SM4 Algorithm with the SIMD Instruction Set[J]. Journal of Computer Research and Development, 2024, 61(8): 2097-2109. DOI: 10.7544/issn1000-1239.202220531
[4]	Shen Jie, Long Biao, Jiang Hao, Huang Chun. Implementation and Optimization of Vector Trigonometric Functions on Phytium Processors[J]. Journal of Computer Research and Development, 2020, 57(12): 2610-2620. DOI: 10.7544/issn1000-1239.2020.20190721
[5]	Yan Hongfei, Zhang Xudong, Shan Dongdong, Mao Xianling, Zhao Xin. SIMD-Based Inverted Index Compression Algorithms[J]. Journal of Computer Research and Development, 2015, 52(5): 995-1004. DOI: 10.7544/issn1000-1239.2015.20131548
[6]	Zhao Long, Han Wenbao, and Yang Hongzhi. Research on ECC Attacking Algorithm Based on SIMD Instructions[J]. Journal of Computer Research and Development, 2012, 49(7): 1553-1559.
[7]	He Yi, Ren Ju, Wen Mei, Yang Qianming, Wu Nan, Zhang Chunyuan, and Guo Min. Research on FPGA-Based Paging-Simulation Model for SIMD Architecture[J]. Journal of Computer Research and Development, 2011, 48(1): 9-18.
[8]	Huang Shuangqu, Xiang Bo, Bao Dan, Chen Yun, and Zeng Xiaoyang. VLSI Implementation of Multi-Standard LDPC Decoder Based on SIMD Architecture[J]. Journal of Computer Research and Development, 2010, 47(7): 1313-1320.
[9]	Li Zhaopeng, Chen Yiyun, Ge Lin, and Hua Baojian. A Formal Certifying Framework for Assembly Programs[J]. Journal of Computer Research and Development, 2008, 45(5): 825-833.
[10]	Lin Jiao, Chen Wenguang, Li Qiang, Zheng Weimin, Zhang Yimin. A New Data Clustering Algorithm for Parallel Whole-Genome Shotgun Sequence Assembly[J]. Journal of Computer Research and Development, 2006, 43(8): 1323-1329.