Spatial-Temporal Transformer Networks for Traffic Flow Forecasting

TL;DR

This paper introduces Spatial-Temporal Transformer Networks (STTNs) that effectively model dynamic spatial and long-range temporal dependencies for improved long-term traffic flow forecasting, outperforming existing methods.

Contribution

The paper proposes a novel STTN framework combining dynamic spatial transformers and temporal transformers to enhance long-term traffic prediction accuracy.

Findings

Achieves competitive results on PeMS datasets.

Enables fast and scalable training for long-range dependencies.

Improves long-term traffic flow forecasting accuracy.

Abstract

Traffic forecasting has emerged as a core component of intelligent transportation systems. However, timely accurate traffic forecasting, especially long-term forecasting, still remains an open challenge due to the highly nonlinear and dynamic spatial-temporal dependencies of traffic flows. In this paper, we propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) that leverages dynamical directed spatial dependencies and long-range temporal dependencies to improve the accuracy of long-term traffic forecasting. Specifically, we present a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies with self-attention mechanism to capture realtime traffic conditions as well as the directionality of traffic flows. Furthermore, different spatial dependency patterns can be jointly modeled with multi-heads attention mechanism to consider diverse relationships related to different factors (e.g. similarity, connectivity and covariance). On the other hand, the temporal transformer is utilized to model long-range bidirectional temporal dependencies across multiple time steps. Finally, they are composed as a block to jointly model the spatial-temporal dependencies for accurate traffic prediction. Compared to existing works, the proposed model enables fast and scalable training over a long range spatial-temporal dependencies. Experiment results demonstrate that the proposed model achieves competitive results compared with the state-of-the-arts, especially forecasting long-term traffic flows on real-world PeMS-Bay and PeMSD7(M) datasets.