Abstract: Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (3) inherent difficulty of long-term forecasting. To address these challenges, we propose to model the traffic flow as a diffusion process on a directed graph and introduce Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow. Specifically, DCRNN captures the spatial dependency using bidirectional random walks on the graph, and the temporal dependency using the encoder-decoder architecture with scheduled sampling. We evaluate the framework on two real-world large-scale road network traffic datasets and observe consistent improvement of 12% - 15% over state-of-the-art baselines
Keywords: Traffic prediction, spatiotemporal forecasting, diffusion, graph convolution, random walk, long-term forecasting
TL;DR: A neural sequence model that learns to forecast on a directed graph.
Code: [![github](/images/github_icon.svg) liyaguang/DCRNN](https://github.com/liyaguang/DCRNN) + [![Papers with Code](/images/pwc_icon.svg) 13 community implementations](https://paperswithcode.com/paper/?openreview=SJiHXGWAZ)
Data: [METR-LA](https://paperswithcode.com/dataset/metr-la), [PEMS-BAY](https://paperswithcode.com/dataset/pems-bay)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 7 code implementations](https://www.catalyzex.com/paper/arxiv:1707.01926/code)