MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting

Yoli Shavit, Jacob Goldberger
10/8/2025
cs.LGcs.AI

Official code: yolish/moe_unc_tsf (2 stars, MIT, last commit 2026-04-30).

Abstract

We introduce Mixture-of-Gaussians with Uncertainty-based Gating (MoGU), a novel Mixture-of-Experts (MoE) framework designed for regression tasks and applied to time series forecasting. Unlike conventional MoEs that provide only point estimates, MoGU models each expert's output as a Gaussian distribution. This allows it to directly quantify both the forecast (the mean) and its inherent uncertainty (variance). MoGU's core innovation is its uncertainty-based gating mechanism, which replaces the traditional input-based gating network by using each expert's estimated variance to determine its contribution to the final prediction. Evaluated across diverse time series forecasting benchmarks, MoGU consistently outperforms single-expert models and traditional MoE setups. It also provides well-quantified, informative uncertainties that directly correlate with prediction errors, enhancing forecast reliability. Our code is available from: https://github.com/yolish/moe_unc_tsf

View on arXivView PDF

Code Implementations(1)

yolish/moe_unc_tsfOfficial100%
MIT
21Shell, PythonAug 1, 20255 months agoMIT

Similar Papers

Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting

86% match2025

GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts

83% match2025

TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization

82% match2026

Let Experts Feel Uncertainty: A Multi-Expert Label Distribution Approach to Probabilistic Time Series Forecasting

82% match2026

MoWE : A Mixture of Weather Experts

81% match2025

Filtered not Mixed: Stochastic Filtering-Based Online Gating for Mixture of Large Language Models

81% match1 repo32024

Cite this paper

@article{shavit2025mogu,
  title  = {MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting},
  author = {Yoli Shavit and Jacob Goldberger},
  year   = {2025},
  eprint = {2510.07459},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.07459v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.07459.svg)](https://codeofpaper.com/paper/2510.07459)

Discussion