As one of the important tools for spatial feature extraction, graph
convolution has been applied in a wide range of fields such as traffic flow
prediction. However, current popular works of graph convolution cannot
guarantee spatio-temporal consistency in a long period. The ignorance of
correlational dynamics, convolutional locality and temporal comprehensiveness
would limit predictive accuracy. In this paper, a novel Attention-based Dynamic
Graph Convolutional Recurrent Neural Network (ADGCRNN) is proposed to improve
traffic flow prediction in highway transportation. Three temporal resolutions
of data sequence are effectively integrated by self-attention to extract
characteristics; multi-dynamic graphs and their weights are dynamically created
to compliantly combine the varying characteristics; a dedicated gated kernel
emphasizing highly relative nodes is introduced on these complete graphs to
reduce overfitting for graph convolution operations. Experiments on two public
datasets show our work better than state-of-the-art baselines, and case studies
of a real Web system prove practical benefit in highway transportation.

提出了一种名为 ADGCRNN 的注意力机制动态图卷积循环神经网络，用于改善高速公路交通中的交通流量预测，通过注意力机制有效地整合了三种时间分辨率的数据序列，动态创建多动态图以结合动态特征，引入专注于高相关节点的门控核以减少图卷积操作的过拟合，实验证明该方法优于现有技术基线。