Highlights We develop a new tensor completion framework-LSTC-for large-scale traffic data. LSTC transforms the large problem into a series of small subproblems for each day. We introduce unitary linear transforms to preserve the correlation among subproblems. We use Tubal nuclear norm minimization to achieve global consistency. We use quadratic variation minimization to achieve local smoothness.

    Abstract Missing value problem in spatiotemporal traffic data has long been a challenging topic, in particular for large-scale and high-dimensional data with complex missing mechanisms and diverse degrees of missingness. Recent studies based on tensor nuclear norm have demonstrated the superiority of tensor learning in imputation tasks by effectively characterizing the complex correlations/dependencies in spatiotemporal data. However, despite the promising results, these approaches do not scale well to large data tensors. In this paper, we focus on addressing the missing data imputation problem for large-scale spatiotemporal traffic data. To achieve both high accuracy and efficiency, we develop a scalable tensor learning model—Low-Tubal-Rank Smoothing Tensor Completion (LSTC-Tubal)—based on the existing framework of Low-Rank Tensor Completion, which is well-suited for spatiotemporal traffic data that is characterized by multidimensional structure of location × time of day × day. In particular, the proposed LSTC-Tubal model involves a scalable tensor nuclear norm minimization scheme by integrating linear unitary transformation. Therefore, tensor nuclear norm minimization can be solved by singular value thresholding on the transformed matrix of each day while the day-to-day correlation can be effectively preserved by the unitary transform matrix. Before setting up the experiment, we consider some real-world data sets, including two large-scale 5-min traffic speed data sets collected by the California PeMS system with 11160 sensors: 1) PeMS-4W covers the data over 4 weeks (i.e., 288 × 28 time points), and 2) PeMS-8W covers the data over 8 weeks (i.e., 288 × 56 time points). We compare LSTC-Tubal with some state-of-the-art baseline models, and find that LSTC-Tubal can achieve competitively accuracy with a significantly lower computational cost. In addition, the LSTC-Tubal will also benefit other tasks in modeling large-scale spatiotemporal traffic data, such as network-level traffic forecasting.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Scalable low-rank tensor learning for spatiotemporal traffic data imputation


    Contributors:
    Chen, Xinyu (author) / Chen, Yixian (author) / Saunier, Nicolas (author) / Sun, Lijun (author)


    Publication date :

    2021-05-13




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation

    Chen, Xinyu / Lei, Mengying / Saunier, Nicolas et al. | IEEE | 2022





    Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation

    Ben Said, Ahmed / Erradi, Abdelkarim | IEEE | 2022