WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting
This addresses the problem of high computational costs in deep learning models for time series forecasting, offering a more efficient solution, though it appears incremental as it builds on existing CNN approaches.
The paper tackles time series forecasting by proposing WinNet, a CNN-based model with only one convolutional layer that achieves state-of-the-art performance on eight benchmark datasets while reducing computational complexity.
Deep learning models have recently achieved significant performance improvements in time series forecasting. We present a highly accurate and simply structured CNN-based model with only one convolutional layer, called WinNet, including (i) Sub-window Division block to transform the series into 2D tensor, (ii) Dual-Forecasting mechanism to capture the short- and long-term variations, (iii) Two-dimensional Hybrid Decomposition (TDD) block to decompose the 2D tensor into the trend and seasonal terms to eliminate the non-stationarity, and (iv) Decomposition Correlation Block (DCB) to leverage the correlation between the trend and seasonal terms by the convolution layer. Results on eight benchmark datasets demonstrate that WinNet can achieve SOTA performance and lower computational complexity over CNN-, MLP- and Transformer-based methods. The code will be available at: https://github.com/ouwen18/WinNet.