Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction

TLDR

Traffic prediction is increasingly important for real‑world applications, yet existing models assume stationary spatial dependence and strictly periodic temporal dynamics, which do not reflect the dynamic spatial relationships and shifting temporal patterns observed in practice. This study observes that spatial dependencies are dynamic and temporal patterns shift daily and weekly, and aims to address these issues with a unified framework. The authors introduce the Spatial‑Temporal Dynamic Network, which uses a flow‑gating mechanism to learn dynamic spatial similarity and a periodically shifted attention module to capture non‑periodic temporal shifts. Experimental results on real‑world traffic datasets demonstrate that the proposed STDN outperforms prior methods by effectively modeling dynamic spatial and temporal dependencies.

Abstract

Traffic prediction has drawn increasing attention in AI research field due to the increasing availability of large-scale traffic data and its importance in the real world. For example, an accurate taxi demand prediction can assist taxi companies in pre-allocating taxis. The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. To address these two issues, we propose a novel Spatial-Temporal Dynamic Network (STDN), in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting. To the best of our knowledge, this is the first work that tackle both issues in a unified framework. Our experimental results on real-world traffic datasets verify the effectiveness of the proposed method.