Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mei Wu, Wenchao Weng, Jun Li, Yiqian Lin, Jing Chen, Dewen Seng

TL;DR

An innovative traffic flow prediction network, SFADNet, is proposed, which categorizes traffic flow into multiple traffic patterns based on temporal and spatial feature matrices, and outperforms current state-of-the-art baselines across four large-scale datasets.

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.

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

TL;DR

An innovative traffic flow prediction network, SFADNet, is proposed, which categorizes traffic flow into multiple traffic patterns based on temporal and spatial feature matrices, and outperforms current state-of-the-art baselines across four large-scale datasets.

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.
Paper Structure (14 sections, 10 equations, 3 figures, 5 tables)

This paper contains 14 sections, 10 equations, 3 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Dynamic Graph Generation Module
  4. Decouple Module
  5. Residual Graph Convolution Module
  6. Temporal Sequence Module
  7. Output and Training Strategy
  8. Experiments
  9. Datasets
  10. Baseline Methods
  11. Experiment Settings
  12. Experiment Results
  13. Ablation Experiments
  14. Conclusion

Figures (3)

  • Figure 1: An example of dynamic spatio-temporal relationships in multimodal transportation
  • Figure 2: The framework of SFADNet
  • Figure 3: Diagram of Model Components