FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting

TL;DR

FasterSTS introduces an efficient spatio-temporal graph convolutional network that improves traffic flow prediction accuracy while reducing model complexity by capturing complex correlations more effectively.

Contribution

It presents a novel, faster, and more effective spatio-temporal synchronous model for traffic forecasting, addressing performance and complexity limitations of existing methods.

Findings

Enhanced prediction accuracy over baseline models

Reduced computational complexity

Effective modeling of complex spatio-temporal heterogeneity

Abstract

Accurate traffic flow prediction heavily relies on the spatio-temporal correlation of traffic flow data. Most current studies separately capture correlations in spatial and temporal dimensions, making it difficult to capture complex spatio-temporal heterogeneity, and often at the expense of increasing model complexity to improve prediction accuracy. Although there have been groundbreaking attempts in the field of spatio-temporal synchronous modeling, significant limitations remain in terms of performance and complexity control.This study proposes a quicker and more effective spatio-temporal synchronous traffic flow forecast model to address these issues.