Sorry, you need to enable JavaScript to visit this website.

WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting

DOI:
10.60864/yc4q-6s72
Citation Author(s):
Peiyuan Liu, Beiliang Wu, Naiqi Li, Tao Dai, Fengmao Lei, Jigang Bao, Yong Jiang, Shu-Tao Xia
Submitted by:
Peiyuan Liu
Last updated:
6 June 2024 - 10:50am
Document Type:
Poster
Document Year:
2024
Event:
 

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.

up
1 user has voted: Peiyuan Liu