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›FiLM: Frequency Improved Legendre Memory Model
Machine learningTime-series forecasting

FiLM: Frequency Improved Legendre Memory Model

FiLM (Frequency Improved Legendre Memory Model) · Also known as: Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli

FiLM is a long-term time-series forecasting architecture introduced by Tian Zhou and colleagues at NeurIPS 2022. It combines Legendre polynomial projections of the historical input with learnable frequency-domain filters applied to the resulting coefficient sequences. By representing history as a compact set of polynomial coefficients and filtering those coefficients in the frequency domain, FiLM enables efficient extrapolation over long prediction horizons without the quadratic cost of full self-attention.

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.

FiLM
AutoformerFEDformerState Space ModelFreTS

When to use it

FiLM suits long-horizon univariate and multivariate time-series forecasting tasks where the series exhibit trend and periodic structure. It is a strong baseline when Transformer-based models are too expensive or when input sequences are very long. It assumes stationarity or slow non-stationarity and works best when dominant frequencies are stable across the look-back window. For highly irregular, event-driven, or non-stationary series, recurrent or diffusion-based approaches may be preferable.

Strengths & limitations

Strengths
  • Linear computational complexity in sequence length, enabling very long look-back windows
  • Compact Legendre memory compresses history without information loss up to order K
  • Frequency-domain filtering provides an interpretable mechanism for denoising
  • Competitive long-horizon forecasting accuracy with a simple, lightweight architecture
Limitations
  • Polynomial order K is a sensitive hyperparameter; too low loses detail, too high overfits
  • Assumes that dominant frequencies in the look-back window are representative of future patterns
  • Limited capacity to model abrupt distributional shifts or sudden regime changes
  • Multivariate channel mixing is basic compared to dedicated cross-variable attention mechanisms

Frequently asked

How does FiLM differ from FEDformer and Autoformer?

FEDformer and Autoformer retain a Transformer backbone with frequency-enhanced or autocorrelation-based attention. FiLM replaces the attention mechanism entirely with Legendre polynomial projection and frequency filtering, yielding a simpler architecture with linear complexity and no attention computation.

What is the role of Legendre polynomials in FiLM?

Legendre polynomials form an orthogonal basis on a bounded interval. Projecting the look-back window onto this basis compresses the input into K coefficients that capture different temporal scales. This projection is lossless up to the chosen order and provides a natural analytical form for extrapolation beyond the observed window.

Does FiLM require GPU acceleration for practical use?

FiLM's linear complexity means it can run on CPUs for moderate sequence lengths and forecast horizons. However, GPU acceleration is recommended for training on large datasets or when using high polynomial orders K, as the frequency-domain matrix operations benefit significantly from parallel hardware.

Sources

  1. Zhou, T., Ma, Z., Wen, Q., Sun, L., Yao, T., Yin, W., & Jin, R. (2022). FiLM: Frequency improved Legendre memory model for long-term time series forecasting. NeurIPS. link ↗

How to cite this page

ScholarGate. (2026, June 2). FiLM (Frequency Improved Legendre Memory Model). ScholarGate. https://scholargate.app/en/deep-learning/film

Related methods

AutoformerFEDformerState Space Model

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.

  • AutoformerDeep learning↔ compare
  • FEDformerDeep learning↔ compare
  • State Space ModelEconometrics↔ compare
Compare side by side →

Referenced by

FEDformerFreTS

Similar methods

FEDformerFreTSAutoformerNon-stationary TransformerLightTSTimeMixerETSformerTemporal Fusion Transformer

Related reference concepts

Convolutional and Sequence ModelsSequence-to-Sequence Models and TransformersDeep Generative ModelsMachine LearningNeural Network ArchitecturesBias-Variance and Overfitting

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

ScholarGate — FiLM (FiLM (Frequency Improved Legendre Memory Model)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/film · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Tian Zhou et al.
Year
2022
Type
Frequency-domain time-series forecasting model
Subfamily
Time-series forecasting
Venue
NeurIPS 2022
Complexity
Linear in sequence length
Related methods
AutoformerFEDformerState Space Model
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