SFADNet: Spatio-temporal Fused Graph based on Attention Decoupling Network for Traffic Prediction

TL;DR

SFADNet is a novel traffic prediction model that uses adaptive spatio-temporal graphs and attention mechanisms to better capture dynamic relationships, significantly improving accuracy over existing methods.

Contribution

Introduces SFADNet, a new network that models traffic flow with pattern-based spatio-temporal graphs and attention decoupling, enhancing prediction precision.

Findings

SFADNet outperforms state-of-the-art baselines on four large-scale datasets.

The model effectively captures dynamic spatio-temporal relationships.

Attention decoupling improves the modeling of complex traffic patterns.

Abstract

In recent years, traffic flow prediction has played a crucial role in the management of intelligent transportation systems. However, traditional prediction methods are often limited by static spatial modeling, making it difficult to accurately capture the dynamic and complex relationships between time and space, thereby affecting prediction accuracy. This paper proposes an innovative traffic flow prediction network, SFADNet, which categorizes traffic flow into multiple traffic patterns based on temporal and spatial feature matrices. For each pattern, we construct an independent adaptive spatio-temporal fusion graph based on a cross-attention mechanism, employing residual graph convolution modules and time series modules to better capture dynamic spatio-temporal relationships under different fine-grained traffic patterns. Extensive experimental results demonstrate that SFADNet outperforms current state-of-the-art baselines across four large-scale datasets.