Papers › Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting

Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting

13 Oct 2021arXiv:2110.08255archive 2025-07-28

Kiran Madhusudhanan, Johannes Burchert, Nghia Duong-Trung, Stefan Born, Lars Schmidt-Thieme

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

18kiran12/Yformer-Time-Series-Forecasting officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderTime SeriesTime Series AnalysisTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPEConcatenated Skip ConnectionConvolutionCosine AnnealingDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxSparse TransformerTransformerU-NetWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections