The Traffic flow forecasting (TFF) problem is essential to modern intelligent transport systems (ITS). Massive flow data from contemporary transport systems have put forward the challenge of effectively capturing both the latent spatial patterns and the temporal dynamics of traffic flow data, when an ITS is doing forecasting. To cope with this challenge, we introduce a novel spatial-temporal graph self-attentive model (STGSA) for short-term traffic flow forecasting. Our model learns graph-level spatial embedding using graph self-attention layers with Gumbel-Softmax technique, and the temporal embedding leveraging RNN cells integrated with Gated Recurrent Units. We evaluate the effectiveness of our proposed method on the traffic flow data of Langfang, China throughout the year of 2014, and it outperforms most of the state-of-the-art baselines.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning Dynamic Graph Embedding for Traffic Flow Forecasting: A Graph Self-Attentive Method


    Contributors:
    Kang, Zifeng (author) / Xu, Hanwen (author) / Hu, Jianming (author) / Pei, Xin (author)


    Publication date :

    2019-10-01


    Size :

    2564767 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting

    Hu, Yongli / Peng, Ting / Guo, Kan et al. | Wiley | 2023

    Free access

    DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting

    Alessio Monti / Alessia Bertugli / Simone Calderara et al. | BASE | 2021

    Free access

    Urban Traffic Flow Forecasting Based on Graph Structure Learning

    Guangyu Huo / Yong Zhang / Yimei Lv et al. | DOAJ | 2024

    Free access