Wavelet-Inspired Multiscale Graph Convolutional Recurrent Network for Traffic Forecasting

arXiv:2401.06040v2 Announce Type: replace
Abstract: Traffic forecasting is the foundation for intelligent transportation systems. Spatiotemporal graph neural networks have demonstrated state-of-the-art performance in traffic forecasting. However, these methods do not explicitly model some of the natural characteristics in traffic data, such as the multiscale structure that encompasses spatial and temporal variations at different levels of granularity or scale. To that end, we propose a Wavelet-Inspired Graph Convolutional Recurrent Network (WavGCRN) which combines multiscale analysis (MSA)-based method with Deep Learning (DL)-based …

abstract art arxiv cs.lg data forecasting foundation graph graph neural networks intelligent intelligent transportation natural network networks neural networks performance spatial state systems temporal traffic transportation type wavelet