Multi-graph fusion based graph convolutional networks for traffic prediction
Multi-graph fusion based graph convolutional networks for traffic prediction
复制标题
DOI：
10.1016/j.comcom.2023.08.004
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Na Hu;Dafang Zhang;Kun Xie;Wei Liang;Kuan-Ching Li;A. Zomaya
中科院分区：
文献类型：
--
作者：
Na Hu;Dafang Zhang;Kun Xie;Wei Liang;Kuan-Ching Li;A. Zomaya
交通预测对于交通管理和出行路线规划具有重要意义，但由于空间依赖性复杂且时间模式动态，因此交通预测具有挑战性。局部空间依赖关系存在于附近的节点之间，而全局空间依赖关系存在于具有相似流量模式的遥远节点之间。捕获多个空间依赖性的一种直接方法是设计具有多个图卷积网络的预测模型。然而，它带来了较高的内存和参数成本。与基于可学习邻接矩阵的方法相同。此外，现有方法对于时间依赖性建模效率低下。为了克服这些限制，我们提出了一种用于流量预测的基于多图融合的图卷积网络（GFGCN），其中提出了多图融合图卷积模块，而无需构建多个图卷积网络。图卷积网络中的邻接矩阵可以通过格拉斯曼流形上的子空间合并来反映多种空间关系。此外，还设计了一个与注意力机制和扩张卷积网络相结合的时间模块，以有效地对时间动态进行建模。为了验证和分析，对三个真实世界数据集进行了广泛的实验。实验结果表明，所提出的 GFGCN 优于基线，具有更好的预测精度。
Traffic prediction is significant for transportation management and travel route planning, and it is challenging as the spatial dependencies are complex and temporal patterns are dynamic. Local spatial dependencies exist between nodes nearby, and global spatial dependencies are between distant nodes with similar traffic patterns. One direct method to capture multiple spatial dependencies is to design a prediction model with multiple graph convolutional networks. However, it introduces high memory and parameter costs. The same with the learnable adjacency matrix-based approaches. Furthermore, existing methods are inefficient for temporal dependency modeling. To overcome such limitations, we propose a multi-Graph Fusion-based Graph Convolutional Network (GFGCN) for traffic prediction, where a multi-graph fused graph convolutional module is proposed without building multiple graph convolutional networks. The adjacency matrix in one graph convolutional network can reflect multiple spatial relationships through subspace merging on the Grassmann manifold. Moreover, a temporal module combined with the attention mechanism and a dilated convolutional network to model the temporal dynamic efficiently is designed. For validation and analysis, extensive experiments on three real-world datasets are performed. Experimental results show that the proposed GFGCN outperforms the baselines with better prediction accuracy.