Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Yaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu
7/6/2017
cs.LGstat.ML

Official code: liyaguang/DCRNN (1,448 stars, MIT, last commit 2024-12-09).

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.

View on arXivView PDF

Code Implementations(1)

liyaguang/DCRNNOfficial100%
MIT

Implementation of Diffusion Convolutional Recurrent Neural Network in Tensorflow

1,448426PythonDec 8, 20171 years agoMIT
deep-learning-graphsiclr2018spatiotemporal-forecastingtime-seriestraffic-data

Similar Papers

Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

90% match1 repo982018

DDP-GCN: Multi-Graph Convolutional Network for Spatiotemporal Traffic Forecasting

89% match2 repos152019

STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting

88% match1 repo422024

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

88% match1 repo1.2k2017

TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts

88% match1 repo702024

Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting

88% match1 repo1.4k2019

Cite this paper

@article{li2017diffusion,
  title  = {Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting},
  author = {Yaguang Li and Rose Yu and Cyrus Shahabi and Yan Liu},
  year   = {2017},
  eprint = {1707.01926},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1707.01926}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1707.01926.svg)](https://codeofpaper.com/paper/1707.01926)

Discussion