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

TL;DR

This paper introduces Spatio-Temporal Graph Convolutional Networks (STGCN), a deep learning framework that models complex spatial and temporal dependencies in traffic data for improved mid- and long-term forecasting accuracy.

Contribution

The paper presents a novel graph-based deep learning model with convolutional structures that enhances traffic prediction by capturing multi-scale spatio-temporal correlations more efficiently.

Findings

STGCN outperforms state-of-the-art baselines on real-world datasets.

The model trains faster with fewer parameters.

It effectively captures complex spatio-temporal traffic patterns.

Abstract

Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies. In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem on graphs and build the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Experiments show that our model STGCN effectively captures comprehensive spatio-temporal correlations through modeling multi-scale traffic networks and consistently outperforms state-of-the-art baselines on various real-world traffic datasets.