Adaptive Graph Convolution Networks for Traffic Flow Forecasting

Zhengdao Li, Wei Li, Kai Hwang
7/7/2023
cs.LG

Official code: zhengdaoli/AGC-net (12 stars, last commit 2023-09-06).

Abstract

Traffic flow forecasting is a highly challenging task due to the dynamic spatial-temporal road conditions. Graph neural networks (GNN) has been widely applied in this task. However, most of these GNNs ignore the effects of time-varying road conditions due to the fixed range of the convolution receptive field. In this paper, we propose a novel Adaptive Graph Convolution Networks (AGC-net) to address this issue in GNN. The AGC-net is constructed by the Adaptive Graph Convolution (AGC) based on a novel context attention mechanism, which consists of a set of graph wavelets with various learnable scales. The AGC transforms the spatial graph representations into time-sensitive features considering the temporal context. Moreover, a shifted graph convolution kernel is designed to enhance the AGC, which attempts to correct the deviations caused by inaccurate topology. Experimental results on two public traffic datasets demonstrate the effectiveness of the AGC-net\footnote{Code is available at: https://github.com/zhengdaoli/AGC-net} which outperforms other baseline models significantly.

View on arXivView PDF

Code Implementations(1)

zhengdaoli/AGC-netOfficial

AGC-Net (Adaptive Graph Convolution Networks) is an advanced model designed to predict traffic flow. Dataset: METR-LA, PEMS-BAY

121PythonFeb 11, 20223 years ago

Similar Papers

ESGCN: Edge Squeeze Attention Graph Convolutional Network for Traffic Flow Forecasting

89% match2023

Attention-based Dynamic Graph Convolutional Recurrent Neural Network for Traffic Flow Prediction in Highway Transportation

89% match1 repo112023

Dynamic Graph Convolutional Network with Attention Fusion for Traffic Flow Prediction

88% match1 repo222023

A novel hybrid time-varying graph neural network for traffic flow forecasting

88% match2024

Temporal Graph Learning Recurrent Neural Network for Traffic Forecasting

87% match2024

Spatiotemporal Forecasting of Traffic Flow using Wavelet-based Temporal Attention

87% match1 repo32024

Cite this paper

@article{li2023adaptive,
  title  = {Adaptive Graph Convolution Networks for Traffic Flow Forecasting},
  author = {Zhengdao Li and Wei Li and Kai Hwang},
  year   = {2023},
  eprint = {2307.05517},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.05517v1}
}

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/2307.05517.svg)](https://codeofpaper.com/paper/2307.05517)

Discussion