Dynamic Spatiotemporal Graph Neural Network with Tensor Network

Abstract

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.

References in corpus (5)

• WaveNet: A Generative Model for Raw Audio
• Graph Neural Networks: A Review of Methods and Applications
• Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Era of Big Data Processing: A New Approach via Tensor Networks and Tensor Decompositions

Cited by in corpus (2)

• Graph Neural Network for Traffic Forecasting: A Survey
• A Traffic Light Dynamic Control Algorithm with Deep Reinforcement Learning Based on GNN Prediction