Meta Dynamic Graph for Traffic Flow Prediction

2026-01-15

AI Summary

This work addresses the challenge that existing traffic flow prediction methods struggle to effectively capture dynamic variations and spatiotemporal heterogeneity when modeling complex spatiotemporal dependencies. To overcome this limitation, the authors propose MetaDG, a novel framework that explicitly models spatiotemporal dynamics through a dynamic graph neural network. MetaDG jointly generates adaptive adjacency matrices and meta-parameters to cohesively represent heterogeneous spatiotemporal characteristics, thereby transcending the constraints of conventional approaches that model spatial and temporal dependencies separately. By extending dynamic modeling from static topologies to global spatiotemporal interactions, MetaDG offers a more unified and expressive representation. Extensive experiments on four real-world traffic datasets demonstrate that MetaDG significantly outperforms state-of-the-art methods, confirming its effectiveness and strong generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Traffic flow prediction is a typical spatio-temporal prediction problem and has a wide range of applications. The core challenge lies in modeling the underlying complex spatio-temporal dependencies. Various methods have been proposed, and recent studies show that the modeling of dynamics is useful to meet the core challenge. While handling spatial dependencies and temporal dependencies using separate base model structures may hinder the modeling of spatio-temporal correlations, the modeling of dynamics can bridge this gap. Incorporating spatio-temporal heterogeneity also advances the main goal, since it can extend the parameter space and allow more flexibility. Despite these advances, two limitations persist: 1) the modeling of dynamics is often limited to the dynamics of spatial topology (e.g., adjacency matrix changes), which, however, can be extended to a broader scope; 2) the modeling of heterogeneity is often separated for spatial and temporal dimensions, but this gap can also be bridged by the modeling of dynamics. To address the above limitations, we propose a novel framework for traffic prediction, called Meta Dynamic Graph (MetaDG). MetaDG leverages dynamic graph structures of node representations to explicitly model spatio-temporal dynamics. This generates both dynamic adjacency matrices and meta-parameters, extending dynamic modeling beyond topology while unifying the capture of spatio-temporal heterogeneity into a single dimension. Extensive experiments on four real-world datasets validate the effectiveness of MetaDG.

Problem

• traffic flow prediction
• spatio-temporal dependencies
• dynamic modeling
• spatio-temporal heterogeneity
• graph representation

Innovation

• Meta Dynamic Graph
• spatio-temporal dynamics
• dynamic graph
• heterogeneity modeling
• traffic flow prediction