Continuously Evolving Graph Neural Controlled Differential Equations for Traffic Forecasting

TL;DR

This paper introduces CEGNCDE, a novel framework using controlled differential equations to model continuous spatial-temporal dependencies in traffic forecasting, significantly improving prediction accuracy over existing methods.

Contribution

The paper proposes a new continuous graph neural controlled differential equations framework that captures evolving spatial-temporal dependencies for traffic forecasting.

Findings

CEGNCDE outperforms state-of-the-art methods in accuracy metrics.

The continuous modeling approach effectively captures dynamic dependencies.

Experimental results show consistent improvements across multiple datasets.

Abstract

As a crucial technique for developing a smart city, traffic forecasting has become a popular research focus in academic and industrial communities for decades. This task is highly challenging due to complex and dynamic spatial-temporal dependencies in traffic networks. Existing works ignore continuous temporal dependencies and spatial dependencies evolving over time. In this paper, we propose Continuously Evolving Graph Neural Controlled Differential Equations (CEGNCDE) to capture continuous temporal dependencies and spatial dependencies over time simultaneously. Specifically, a continuously evolving graph generator (CEGG) based on NCDE is introduced to generate the spatial dependencies graph that continuously evolves over time from discrete historical observations. Then, a graph neural controlled differential equations (GNCDE) framework is introduced to capture continuous temporal dependencies and spatial dependencies over time simultaneously. Extensive experiments demonstrate that CEGNCDE outperforms the SOTA methods by average 2.34% relative MAE reduction, 0.97% relative RMSE reduction, and 3.17% relative MAPE reduction.