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.

翻译：近期基于CNN和Transformer的模型尝试利用频率和周期信息进行长期时间序列预测。然而，现有工作大多基于傅里叶变换，难以捕获细粒度局部频率结构。本文提出一种小波-傅里叶变换网络（WFTNet）用于长期时间序列预测。WFTNet联合使用傅里叶变换与小波变换从信号中提取全面的时频信息，其中傅里叶变换捕获全局周期模式，小波变换捕获局部周期模式。此外，我们引入周期加权系数（PWC）自适应平衡全局与局部频率模式的重要性。在多种时间序列数据集上的大量实验表明，WFTNet始终优于其他最先进基线模型。代码见https://github.com/Hank0626/WFTNet。