Time series data is ubiquitous in research as well as in a wide variety of
industrial applications. Effectively analyzing the available historical data
and providing insights into the far future allows us to make effective
decisions. Recent research has witnessed the superior performance of
transformer-based architectures, especially in the regime of far horizon time
series forecasting. However, the current state of the art sparse Transformer
architectures fail to couple down- and upsampling procedures to produce outputs
in a similar resolution as the input. We propose the Yformer model, based on a
novel Y-shaped encoder-decoder architecture that (1) uses direct connection
from the downscaled encoder layer to the corresponding upsampled decoder layer
in a U-Net inspired architecture, (2) Combines the downscaling/upsampling with
sparse attention to capture long-range effects, and (3) stabilizes the
encoder-decoder stacks with the addition of an auxiliary reconstruction loss.
Extensive experiments have been conducted with relevant baselines on four
benchmark datasets, demonstrating an average improvement of 19.82, 18.41
percentage MSE and 13.62, 11.85 percentage MAE in comparison to the current
state of the art for the univariate and the multivariate settings respectively.

该论文提出了一种基于 Y-shaped 编码器 - 解码器结构的 Yformer 模型，结合稀疏注意力和下采样上采样过程，通过在四个基准数据集上进行的实验结果显示，该模型相比当前最先进的模型在一元和多元场景下的平均改进率分别为 19.82％和 18.41％MSE 和 13.62％和 11.85％MAE。