论文标题
带有张量网络的动态时空图神经网络
Dynamic Spatiotemporal Graph Neural Network with Tensor Network
论文作者
论文摘要
动态空间图构造是时间序列数据问题的图神经网络（GNN）的挑战。尽管某些自适应图是可以想象的，但仅将2D图嵌入网络中，以反映当前的空间关系，而不论所有以前的情况如何。在这项工作中，我们生成一个空间张量图（STG），以收集所有动态空间关系以及时间张量图（TTG），以在每个节点处沿时间沿时间沿时间进行潜在模式。这两个张量图共享相同的节点和边缘，这使我们通过投影纠缠的对状态（PEP）探索其纠缠的相关性，以优化这两个图。我们通过实验性地比较了公共流量数据集的基于GNN的最新方法的准确性和时间成本。
Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems. Although some adaptive graphs are conceivable, only a 2D graph is embedded in the network to reflect the current spatial relation, regardless of all the previous situations. In this work, we generate a spatial tensor graph (STG) to collect all the dynamic spatial relations, as well as a temporal tensor graph (TTG) to find the latent pattern along time at each node. These two tensor graphs share the same nodes and edges, which leading us to explore their entangled correlations by Projected Entangled Pair States (PEPS) to optimize the two graphs. We experimentally compare the accuracy and time costing with the state-of-the-art GNN based methods on the public traffic datasets.
