Traffic forecasting is a highly challenging task owing to the dynamical spatio-temporal dependencies of traffic flows. To handle this, we focus on modeling the spatio-temporal dynamics and propose a network termed Edge Squeeze Graph Convolutional Network (ESGCN) to forecast traffic flow in multiple regions. ESGCN consists of two modules: W-module and ES module. W-module is a fully node-wise convolutional network. It encodes the time-series of each traffic region separately and decomposes the time-series at various scales to capture fine and coarse features. The ES module models the spatio-temporal dynamics using Graph Convolutional Network (GCN) and generates an Adaptive Adjacency Matrix (AAM) with temporal features. To improve the accuracy of AAM, we introduce three key concepts. 1) Using edge features to directly capture the spatiotemporal flow representation among regions. 2) Applying an edge attention mechanism to GCN to extract the AAM from the edge features. Here, the attention mechanism can effectively determine important spatio-temporal adjacency relations. 3) Proposing a novel node contrastive loss to suppress obstructed connections and emphasize related connections. Experimental results show that ESGCN achieves state-of-the-art performance by a large margin on four real-world datasets (PEMS03, 04, 07, and 08) with a low computational cost.

翻译：交通流量预测因其动态的时空依赖性而极具挑战。为解决此问题，我们专注于建模时空动态，并提出一种名为边挤压图卷积网络（ESGCN）的网络，用于预测多个区域的交通流量。ESGCN由两个模块组成：W模块和ES模块。W模块是一个全节点式卷积网络，它分别编码每个交通区域的时间序列，并在不同尺度上分解时间序列以捕捉细粒度和粗粒度特征。ES模块利用图卷积网络（GCN）建模时空动态，并生成具有时间特征的自适应邻接矩阵（AAM）。为提高AAM的准确性，我们引入了三个关键概念：1）利用边特征直接捕捉区域间的时空流表示；2）将边注意力机制应用于GCN，从边特征中提取AAM，此处注意力机制能有效确定重要的时空邻接关系；3）提出一种新的节点对比损失，用于抑制受阻连接并强化相关连接。实验结果表明，ESGCN在四个真实数据集（PEMS03、04、07和08）上以较低计算成本大幅领先现有方法，实现了最先进的性能。