Recent studies have demonstrated the great success of graph convolutional networks in short-term traffic forecasting (e.g., 15–30 min ahead) tasks by capturing dependencies in road network structure. Based on these models, long-term forecasting can be achieved by two approaches: (1) recursively generating a one-step-ahead prediction and (2) adapting the models to sequence-to-sequence (seq2seq) learning. However, in practice, these two approaches often show poor performance in long-term forecasting tasks. The recursive approach suffers from the error accumulation problem, as the model is trained based on one-step-ahead loss. On the other hand, seq2seq shows convergence issues that limit its application. To address the issues for long-term forecasting, in this paper, we propose a universal framework that directly transforms any existing state-of-the-art models for one-step-ahead prediction to achieve more accurate long-term forecasting. The proposed framework consists of two components—a base model and a bias block. The base model is assumed to be a well-trained state-of-the-art one-step-ahead forecasting model, and the bias block is constructed by a spatiotemporal graph neural network composed of gated temporal convolution layers and graph convolution layers. The base model and the bias block are residually-connected so that we can substantially reduce the training complexity. Extensive experiments are conducted on existing benchmark datasets. We experiment with several state-of-the-art models in the literature as base models, and our results demonstrate the ability of the proposed universal framework to greatly improve the long-term prediction accuracy for all models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Universal Framework of Spatiotemporal Bias Block for Long-Term Traffic Forecasting


    Beteiligte:
    Liu, Fuqiang (Autor:in) / Wang, Jiawei (Autor:in) / Tian, Jingbo (Autor:in) / Zhuang, Dingyi (Autor:in) / Miranda-Moreno, Luis (Autor:in) / Sun, Lijun (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2022


    Format / Umfang :

    2887910 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fast Spatiotemporal Learning Framework for Traffic Flow Forecasting

    Guo, Canyang / Chen, Chi-Hua / Hwang, Feng-Jang et al. | IEEE | 2023



    Spatiotemporal traffic forecasting: review and proposed directions

    Ermagun, Alireza / Levinson, David | Taylor & Francis Verlag | 2018


    Adaptive Spatiotemporal InceptionNet for Traffic Flow Forecasting

    Wang, Yi / Jing, Changfeng / Huang, Wei et al. | IEEE | 2023