<b>Multidynamic Temporal Representation Graph Convolutional Network for Traffic Flow Prediction</b>

1. We propose a novel traffic flow prediction model (MDTRGCN), a dynamic spatial dependency learning approach that propagates node hidden states on the basis of dynamic spatial relationships to capture dynamic spatiotemporal features, enabling effective long-term predictions.2. We construct a dynamic graph builder and dynamic graph convolutions, and through the multidimensional fusion module, we integrate auxiliary hidden states with the main hidden states in both spatial and temporal dimensions to uncover dynamic spatiotemporal relationships.3. We design a temporal representation learning method that pretrains through a masked reconstruction task to obtain compressed and contextual temporal representations of subsequences, capturing periodic features in long historical sequences.4. Extensive experimental results on two real-world datasets demonstrate that the MDTRGCN outperforms baseline methods in terms of prediction accuracy.1. 本研究提出一种新型交通流预测模型MDTRGCN，该模型属于动态空间依赖学习方法，基于动态空间关联传播节点隐状态以捕捉动态时空特征，可实现有效的长期预测。 2. 本研究构建了动态图构建器与动态图卷积模块，并通过多维融合模块在空间与时间维度上将辅助隐状态与主隐状态进行融合，以挖掘动态时空关联关系。 3. 本研究设计了一种时序表征学习方法，该方法通过掩码重构任务进行预训练，以获取子序列的压缩且具备上下文信息的时序表征，进而捕捉长历史序列中的周期性特征。 4. 在两个真实世界数据集上开展的大量实验结果表明，MDTRGCN的预测精度优于各类基线方法。