Fourier-Mixed Window Attention: Accelerating Informer for Long Sequence Time-Series Forecasting

Abstract

We study a fast local-global window-based attention method to accelerate Informer for long sequence time-series forecasting. While window attention being local is a considerable computational saving, it lacks the ability to capture global token information which is compensated by a subsequent Fourier transform block. Our method, named FWin, does not rely on query sparsity hypothesis and an empirical approximation underlying the ProbSparse attention of Informer. Through experiments on univariate and multivariate datasets, we show that FWin transformers improve the overall prediction accuracies of Informer while accelerating its inference speeds by 1.6 to 2 times. We also provide a mathematical definition of FWin attention, and prove that it is equivalent to the canonical full attention under the block diagonal invertibility (BDI) condition of the attention matrix. The BDI is shown experimentally to hold with high probability for typical benchmark datasets.

arXiv comment19 pages (main), 11 pages (appendix), 8 figures

References in corpus (7)

• MLP-Mixer: An all-MLP Architecture for Vision
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
• MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
• Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System