FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
This addresses efficiency and accuracy issues in time series forecasting for applications like finance or weather prediction, representing an incremental improvement over existing Transformer methods.
The paper tackles the computational expense and inability to capture global trends in Transformer-based long-term series forecasting by proposing FEDformer, which combines Transformer with seasonal-trend decomposition and frequency enhancement, reducing prediction error by 14.8% for multivariate and 22.6% for univariate series compared to state-of-the-art methods.
Although Transformer-based methods have significantly improved state-of-the-art results for long-term series forecasting, they are not only computationally expensive but more importantly, are unable to capture the global view of time series (e.g. overall trend). To address these problems, we propose to combine Transformer with the seasonal-trend decomposition method, in which the decomposition method captures the global profile of time series while Transformers capture more detailed structures. To further enhance the performance of Transformer for long-term prediction, we exploit the fact that most time series tend to have a sparse representation in well-known basis such as Fourier transform, and develop a frequency enhanced Transformer. Besides being more effective, the proposed method, termed as Frequency Enhanced Decomposed Transformer ({\bf FEDformer}), is more efficient than standard Transformer with a linear complexity to the sequence length. Our empirical studies with six benchmark datasets show that compared with state-of-the-art methods, FEDformer can reduce prediction error by $14.8\%$ and $22.6\%$ for multivariate and univariate time series, respectively. Code is publicly available at https://github.com/MAZiqing/FEDformer.