WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting
This addresses the problem of accurate long-term forecasting in time series analysis, with incremental improvements over existing methods.
The paper tackles long-term time series forecasting by proposing WFTNet, which combines Fourier and wavelet transforms to capture global and local periodicity, and it consistently outperforms state-of-the-art baselines in experiments.
Recent CNN and Transformer-based models tried to utilize frequency and periodicity information for long-term time series forecasting. However, most existing work is based on Fourier transform, which cannot capture fine-grained and local frequency structure. In this paper, we propose a Wavelet-Fourier Transform Network (WFTNet) for long-term time series forecasting. WFTNet utilizes both Fourier and wavelet transforms to extract comprehensive temporal-frequency information from the signal, where Fourier transform captures the global periodic patterns and wavelet transform captures the local ones. Furthermore, we introduce a Periodicity-Weighted Coefficient (PWC) to adaptively balance the importance of global and local frequency patterns. Extensive experiments on various time series datasets show that WFTNet consistently outperforms other state-of-the-art baseline. Code is available at https://github.com/Hank0626/WFTNet.