Researchers propose FreMo, a lightweight model that explicitly exploits the frequency domain to address challenges in multi-modality transportation forecasting caused by distinct spectral characteristics and uneven interactions across frequencies.
- The architecture introduces a Modality-Wise Frequency Filter (MFF) to adaptively refine spectral components within each modality, emphasizing informative frequencies while suppressing noise.
- It incorporates a Frequency-Guided Synergy Integrator (FSI) that selectively aggregates information across modalities based on their relative contribution at each frequency.
- FreMo supports plug-and-play integration with general time series backbones by disentangling modality-wise spectral refinement from cross-modality synergy.
Extensive experiments on real-world datasets show that FreMo consistently outperforms state-of-the-art baselines, demonstrating superior performance and generalization across diverse forecasting scenarios.