Liang, Y., Ouyang, K., Wang, Y., Pan, Z., Yin, Y., Chen, H., Zhang, J., Zheng, Y., Rosenblum, D. S., & Zimmermann, R. (2023). Mixed-Order Relation-Aware Recurrent Neural Networks for Spatio-Temporal Forecasting. IEEE Transactions on Knowledge and Data Engineering, 35(9), 9254–9268. https://doi.org/10.1109/tkde.2022.3222373
Abstract:
Spatio-temporal forecasting has a wide range of applications in smart city efforts, such as traffic forecasting and air quality prediction. Graph Convolutional Recurrent Neural Networks (GCRNN) are the state-of-the-art methods for this problem, which learn temporal dependencies by RNNs and exploit pairwise node proximity to model spatial dependencies. However, the spatial relations in real data are not simply pairwise but sometimes in a higher order among multiple nodes. Moreover, spatio-temporal sequences deriving from nature are often regulated by known or unknown physical laws. GCRNNs rarely take into account the underlying physics in real-world systems, which may result in degenerated performance. To address these issues, we devise a general model called Mixed-Order Relation-Aware RNN (MixRNN+) for spatio-temporal forecasting. Specifically, our MixRNN+ captures the complex mixed-order spatial relations of nodes through a newly proposed building block called Mixer, and simultaneously addressing the underlying physics by the integration of a new residual update strategy. Experimental results on three forecasting tasks in smart city applications (including traffic speed, taxi flow, and air quality prediction) demonstrate the superiority of our model against the state-of-the-art methods. We have also deployed a cloud-based system using our method as the bedrock model to show its practicality.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Ministry of Education - Academic Research Fund Tier 2
Grant Reference no. : T2EP20221-0023
This research is also supported by the Beijing Nova Program (Z201100006820053), and the Beijing Natural Science Foundation (4212021). Supported in part by the funding project of Zhejiang Lab under Grant 2020LC0PI01.