Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Non-stationary Transformer
Machine learningTime-series forecasting

Non-stationary Transformer

Non-stationary Transformers for Forecasting · Also known as: NS-Transformer, Non-stationary Transformer Network, Stationarization-based Transformer, Durağan-Olmayan Transformer

Non-stationary Transformer is a Transformer-based time-series forecasting architecture introduced by Yong Liu, Haixu Wu, Jianmin Wang, and Mingsheng Long at NeurIPS 2022. It addresses a fundamental tension in applying Transformers to real-world time series: over-stationarization during preprocessing strips out non-stationary signals that carry predictive information, while raw non-stationary inputs cause attention to collapse. The model resolves this through series stationarization paired with a novel de-stationary attention mechanism that restores the original temporal distribution in predictions.

ScholarGate
  1. Machine learning
  2. v1
  3. 1 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Non-stationary Transformer
Augmented Dickey-Fuller…AutoformerInformerKoopa

When to use it

Use Non-stationary Transformer when forecasting multivariate or univariate time series that exhibit clear non-stationarity (trends, level shifts, varying variance) over medium to long horizons. It assumes a fixed-length look-back window and requires sufficient training data to learn temporal patterns. It is less suited to very short series or cases where non-stationarity is sparse. Alternatives include Autoformer for longer sequences with strong periodicity, or simple linear models when data volumes are small.

Strengths & limitations

Strengths
  • Explicitly handles non-stationary time series without discarding trend or scale information
  • De-stationary attention is lightweight and integrates into any standard Transformer architecture
  • Per-sequence normalization generalizes across series with heterogeneous magnitudes
  • Demonstrated competitive performance on standard long-range forecasting benchmarks against Transformer-family baselines
Limitations
  • Quadratic attention complexity limits scalability to very long sequences without further approximation
  • Performance advantage over simple linear models may be marginal on some univariate benchmarks
  • Requires careful hyperparameter tuning (look-back length, number of layers, tau/delta learning rate)
  • Like all Transformer models, it demands substantial training data and compute compared to classical statistical methods

Frequently asked

How is series stationarization different from standard z-score normalization?

Standard z-score normalization typically uses global statistics computed over the entire training set. Series stationarization in Non-stationary Transformer uses per-sequence statistics — mean and standard deviation computed from each individual input window. This means each sample is normalized relative to itself, preserving relative within-window patterns while removing local level and scale, and the removed statistics are stored for later recovery.

What are the tau and delta operators in de-stationary attention?

Tau and delta are learnable rescaling parameters that are conditioned on the original non-stationary statistics of the input sequence. Tau scales the queries and delta shifts the keys inside the scaled dot-product attention. They allow the attention weights to reflect the original temporal distribution rather than the stationarized one, recovering predictive information that would otherwise be lost after normalization.

Can Non-stationary Transformer be applied to univariate series?

Yes. The architecture supports both univariate and multivariate forecasting. In the univariate case a single channel is processed through the stationarization-attention-recovery pipeline. However, some studies suggest that on certain univariate benchmarks simple linear baselines remain competitive, so practitioners should empirically validate the model against lightweight alternatives before deployment.

Sources

  1. Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. NeurIPS. link ↗

How to cite this page

ScholarGate. (2026, June 2). Non-stationary Transformers for Forecasting. ScholarGate. https://scholargate.app/en/deep-learning/nonstationary-transformer

Related methods

Augmented Dickey-Fuller TestAutoformerInformer

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Augmented Dickey-Fuller TestEconometrics↔ compare
  • AutoformerDeep learning↔ compare
  • InformerDeep learning↔ compare
Compare side by side →

Referenced by

Koopa

Similar methods

iTransformerAutoformerPatchTSTKoopaPyraformerETSformerCrossformerFEDformer

Related reference concepts

Sequence-to-Sequence Models and TransformersConvolutional and Sequence ModelsDeep Generative ModelsSelf-Supervised and Representation LearningEnergy ForecastingBias-Variance and Overfitting

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Non-stationary Transformer (Non-stationary Transformers for Forecasting). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/nonstationary-transformer · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Yong Liu et al.
Year
2022
Type
Transformer-based time-series forecasting model
Subfamily
Time-series forecasting
Venue
NeurIPS 2022
Key Innovation
Series stationarization with de-stationary attention
Related methods
Augmented Dickey-Fuller TestAutoformerInformer
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account