Frequency-Domain Multi-Modality Transportation Modeling

2026-07-09

AI Summary

This work addresses the challenge of effectively modeling heterogeneous spectral characteristics and imbalanced cross-modal frequency interactions in multimodal traffic data. To this end, the authors propose FreMo, a novel framework that pioneers the formulation of multimodal traffic forecasting in the frequency domain. FreMo decouples intra-modal optimization from inter-modal fusion through modality-adaptive spectral filtering and a frequency-guided cross-modal collaboration mechanism. The framework comprises a Modality-level Frequency Filter (MFF) and a Frequency-guided Synergistic Integrator (FSI), both designed as plug-and-play modules compatible with general temporal backbone networks. Extensive experiments demonstrate that FreMo significantly outperforms state-of-the-art methods across multiple real-world datasets, achieving superior prediction accuracy and strong cross-scenario generalization capability.

Abstract

Multi-modality transportation refers to urban systems composed of multiple transportation modes, such as traffic flow and public transit, whose dynamics are coupled by shared temporal patterns. Accurate multi-modality transportation forecasting remains challenging because (1) different modalities exhibit distinct spectral characteristics and (2) interact unevenly across frequencies, whereas most existing methods operate primarily in the time domain or rely on coarse feature fusion. To address these limitations, we propose a lightweight yet effective Frequency-Domain Multi-Modality modeling (FreMo) that explicitly exploits the frequency domain to enable adaptive and selective cross-modality synergy. FreMo disentangles modality-wise spectral refinement from cross-modality synergy and supports plug-and-play integration with general time series backbones. Specifically, FreMo introduces a Modality-Wise Frequency Filter (MFF) to adaptively refine spectral components within each modality, emphasizing informative frequencies while suppressing noise. FreMo further incorporates a Frequency-Guided Synergy Integrator (FSI) that selectively aggregates information across modalities based on their relative contribution at each frequency, facilitating effective cross-modality knowledge sharing while mitigating negative transfer. Extensive experiments on real-world datasets show that FreMo consistently outperforms state-of-the-art baselines, with superior performance and generalization across diverse forecasting scenarios. The code is available at https://github.com/beginner-sketch/FreMo.

Problem

• multi-modality transportation
• frequency domain
• spectral characteristics
• cross-modality interaction
• transportation forecasting

Innovation

• frequency domain
• multi-modality transportation
• spectral refinement
• cross-modality synergy
• adaptive filtering