The Rise of Diffusion Models in Time-Series Forecasting

Caspar Meijer, Lydia Y. Chen
1/5/2024
cs.LGcs.AI

No official code found. Best implementation: AI4HealthUOL/SSSD (335 stars, MIT, last commit 2025-05-24). 1 more below.

Abstract

This survey delves into the application of diffusion models in time-series forecasting. Diffusion models are demonstrating state-of-the-art results in various fields of generative AI. The paper includes comprehensive background information on diffusion models, detailing their conditioning methods and reviewing their use in time-series forecasting. The analysis covers 11 specific time-series implementations, the intuition and theory behind them, the effectiveness on different datasets, and a comparison among each other. Key contributions of this work are the thorough exploration of diffusion models' applications in time-series forecasting and a chronologically ordered overview of these models. Additionally, the paper offers an insightful discussion on the current state-of-the-art in this domain and outlines potential future research directions. This serves as a valuable resource for researchers in AI and time-series analysis, offering a clear view of the latest advancements and future potential of diffusion models.

View on arXivView PDF

Code Implementations(2)

AI4HealthUOL/SSSDCommunity100%
MIT

Repository for the paper: 'Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models'

33555C, C++Aug 19, 20221 years agoMIT
deep-learningdiffusion-modelstime-series-forecastingtime-series-imputation
Capsar/The-Rise-of-Diffusion-Models-in-Time-Series-ForecastingCommunity100%

Literature Survey about the available Diffusion Models capable of Time-Series Forecasting

172TeXJan 5, 20241 years agoNOASSERTION
diffusionforecastingmachine-learningmodelsseries+4 more

Similar Papers

Diffusion Models for Time Series Forecasting: A Survey

95% match2025

Diffusion Models for Time Series Applications: A Survey

94% match2023

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

89% match1 repo1.0k2024

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

88% match1 repo2602023

Series-to-Series Diffusion Bridge Model

87% match2024

Auto-Regressive Moving Diffusion Models for Time Series Forecasting

87% match1 repo1182024

Cite this paper

@article{meijer2024rise,
  title  = {The Rise of Diffusion Models in Time-Series Forecasting},
  author = {Caspar Meijer and Lydia Y. Chen},
  year   = {2024},
  eprint = {2401.03006},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.03006v2}
}

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/2401.03006.svg)](https://codeofpaper.com/paper/2401.03006)

Discussion