Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction

TL;DR

This paper introduces a novel framework combining topology-free pattern preservation with GNNs for traffic speed prediction, using a dual transformer architecture and a distillation learning approach to improve accuracy.

Contribution

It proposes a generic integration paradigm that enhances GNN-based traffic prediction by capturing topology-free patterns through a dual transformer and distillation framework.

Findings

Significant improvement in traffic speed prediction accuracy.

Effective preservation of topology-free patterns.

Versatile framework applicable to existing GNN models.

Abstract

Urban traffic speed prediction aims to estimate the future traffic speed for improving urban transportation services. Enormous efforts have been made to exploit Graph Neural Networks (GNNs) for modeling spatial correlations and temporal dependencies of traffic speed evolving patterns, regularized by graph topology.While achieving promising results, current traffic speed prediction methods still suffer from ignoring topology-free patterns, which cannot be captured by GNNs. To tackle this challenge, we propose a generic model for enabling the current GNN-based methods to preserve topology-free patterns. Specifically, we first develop a Dual Cross-Scale Transformer (DCST) architecture, including a Spatial Transformer and a Temporal Transformer, to preserve the cross-scale topology-free patterns and associated dynamics, respectively. Then, to further integrate both topology-regularized/-free patterns, we propose a distillation-style learning framework, in which the existing GNN-based methods are considered as the teacher model, and the proposed DCST architecture is considered as the student model. The teacher model would inject the learned topology-regularized patterns into the student model for integrating topology-free patterns. The extensive experimental results demonstrated the effectiveness of our methods.