HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting

TL;DR

HyperD is a novel traffic forecasting framework that decouples data into periodic and residual components, effectively capturing multi-scale patterns and irregular fluctuations for improved accuracy and robustness.

Contribution

It introduces a hybrid decoupling approach with specialized modules for periodic and residual data, along with a dual-view alignment loss to enhance separation and modeling.

Findings

Achieves state-of-the-art accuracy on four real-world datasets.

Demonstrates superior robustness under disturbances.

Offers improved computational efficiency.

Abstract

Accurate traffic forecasting plays a vital role in intelligent transportation systems, enabling applications such as congestion control, route planning, and urban mobility optimization. However, traffic forecasting remains challenging due to two key factors: (1) complex spatial dependencies arising from dynamic interactions between road segments and traffic sensors across the network, and (2) the coexistence of multi-scale periodic patterns (e.g., daily and weekly periodic patterns driven by human routines) with irregular fluctuations caused by unpredictable events (e.g., accidents, weather, or construction). To tackle these challenges, we propose HyperD (Hybrid Periodic Decoupling), a novel framework that decouples traffic data into periodic and residual components. The periodic component is handled by the Hybrid Periodic Representation Module, which extracts fine-grained daily and weekly patterns using learnable periodic embeddings and spatial-temporal attention. The residual component, which captures non-periodic, high-frequency fluctuations, is modeled by the Frequency-Aware Residual Representation Module, leveraging complex-valued MLP in frequency domain. To enforce semantic separation between the two components, we further introduce a Dual-View Alignment Loss, which aligns low-frequency information with the periodic branch and high-frequency information with the residual branch. Extensive experiments on four real-world traffic datasets demonstrate that HyperD achieves state-of-the-art prediction accuracy, while offering superior robustness under disturbances and improved computational efficiency compared to existing methods.