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›Time-MoE: Mixture-of-Experts Time-Series Foundation Model
Machine learningTime-series forecasting

Time-MoE: Mixture-of-Experts Time-Series Foundation Model

Time-MoE (Mixture-of-Experts Time-Series Foundation Model) · Also known as: Time Mixture-of-Experts, Time-MoE Foundation Model, Sparse Time-Series Transformer, Zaman Karışık Uzmanlar Modeli

Time-MoE is a billion-scale autoregressive foundation model for universal time-series forecasting, introduced by Shi et al. in 2024 and accepted at ICLR 2025. It combines a decoder-only transformer architecture with sparse Mixture-of-Experts (MoE) feed-forward layers, enabling the model to scale to billions of parameters while activating only a small subset of expert networks per token—dramatically increasing capacity without proportional compute cost.

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.

Time-MoE
ChronosMixture of ExpertsTimesFM

When to use it

Time-MoE is appropriate when you need a general-purpose forecasting foundation model that can generalize across domains without task-specific training. It is particularly well-suited for zero-shot or few-shot forecasting on univariate series, large-scale deployments where inference efficiency matters, and settings where labeled data is scarce. Assumptions include well-behaved scalar time series; it is not designed for multivariate cross-series dependency modeling out of the box. Alternatives include TimesFM, Chronos, and Moirai for similar zero-shot settings.

Strengths & limitations

Strengths
  • Scales to billions of parameters with sublinear compute growth via sparse expert activation
  • Strong zero-shot generalization across diverse time-series domains due to large-scale pretraining
  • Multi-resolution forecasting heads allow simultaneous short- and long-horizon predictions from a single model
  • Decoder-only autoregressive design enables flexible context length without architectural changes
Limitations
  • Primarily designed for univariate forecasting; multivariate cross-series relationships require adaptation
  • Large model size demands substantial memory and infrastructure for deployment
  • Autoregressive decoding accumulates prediction errors over long horizons
  • Pretraining data distribution may not cover highly specialized or rare time-series domains

Frequently asked

How does Time-MoE differ from a standard transformer forecasting model?

Standard transformer forecasters use dense feed-forward layers where every parameter is activated for every token. Time-MoE replaces these with sparse MoE blocks, activating only a small subset of expert networks per token. This allows the total parameter count—and thus model capacity—to scale dramatically while keeping per-token compute roughly constant, enabling billion-parameter models at manageable inference cost.

Can Time-MoE handle multivariate time series?

Time-MoE is primarily architected for univariate forecasting, processing each series independently. While it can be applied channel-independently to multivariate data (treating each variable as a separate series), it does not natively model cross-variable dependencies. Tasks requiring explicit inter-series correlation modeling may benefit from purpose-built multivariate models instead.

What is Time-300B and why does it matter?

Time-300B is the large-scale pretraining corpus introduced alongside Time-MoE, comprising hundreds of billions of time-series observations spanning multiple domains including energy, finance, weather, and transportation. Pretraining on this diverse corpus enables Time-MoE to develop general temporal representations that transfer zero-shot to unseen datasets, similar to how web-scale text corpora underpin large language model generalization.

Sources

  1. Shi, X., Wang, S., Nie, Y., Li, D., Ye, Z., Wen, Q., & Jin, M. (2024). Time-MoE: Billion-scale time series foundation models with mixture of experts. ICLR 2025. link ↗

How to cite this page

ScholarGate. (2026, June 2). Time-MoE (Mixture-of-Experts Time-Series Foundation Model). ScholarGate. https://scholargate.app/en/deep-learning/time-moe

Related methods

ChronosMixture of ExpertsTimesFM

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.

  • ChronosDeep learning↔ compare
  • Mixture of ExpertsDeep learning↔ compare
  • TimesFMDeep learning↔ compare
Compare side by side →

Similar methods

TimesFMMoiraiTimeGPTTimeMixerSundialChronosPyraformerTimesNet

Related reference concepts

Sequence-to-Sequence Models and TransformersEnergy ForecastingConvolutional and Sequence ModelsSelf-Supervised and Representation LearningDeep Generative ModelsMachine Learning

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

ScholarGate — Time-MoE (Time-MoE (Mixture-of-Experts Time-Series Foundation Model)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/time-moe · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Xiaoming Shi et al.
Year
2024
Type
Sparse mixture-of-experts autoregressive foundation model
Subfamily
Time-series forecasting
Parameters
Up to 2.4 billion (sparse activation)
Training Data
Time-300B benchmark corpus
Related methods
ChronosMixture of ExpertsTimesFM
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