LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting

Md Kowsher, Md. Shohanur Islam Sobuj, Nusrat Jahan Prottasha, E. Alejandro Alanis, Ozlem Ozmen Garibay +1 more
10/15/2024
cs.LGcs.CL

No official code found. Best implementation: Kowsher/LLMMixer (42 stars, Apache-2.0, last commit 2024-11-18).

Abstract

Time series forecasting remains a challenging task, particularly in the context of complex multiscale temporal patterns. This study presents LLM-Mixer, a framework that improves forecasting accuracy through the combination of multiscale time-series decomposition with pre-trained LLMs (Large Language Models). LLM-Mixer captures both short-term fluctuations and long-term trends by decomposing the data into multiple temporal resolutions and processing them with a frozen LLM, guided by a textual prompt specifically designed for time-series data. Extensive experiments conducted on multivariate and univariate datasets demonstrate that LLM-Mixer achieves competitive performance, outperforming recent state-of-the-art models across various forecasting horizons. This work highlights the potential of combining multiscale analysis and LLMs for effective and scalable time-series forecasting.

View on arXivView PDF

Code Implementations(1)

Kowsher/LLMMixerCommunity100%
Apache-2.0
428Python, Jupyter NotebookSep 26, 20241 years agoApache-2.0

Similar Papers

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics

91% match2025

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

90% match1 repo172024

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

90% match1 repo1042024

LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting

89% match2024

Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition

89% match2025

Rethinking the Role of LLMs in Time Series Forecasting

89% match2026

Cite this paper

@article{kowsher2024llmmixer,
  title  = {LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting},
  author = {Md Kowsher and Md. Shohanur Islam Sobuj and Nusrat Jahan Prottasha and E. Alejandro Alanis and Ozlem Ozmen Garibay and Niloofar Yousefi},
  year   = {2024},
  eprint = {2410.11674},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.11674v2}
}

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/2410.11674.svg)](https://codeofpaper.com/paper/2410.11674)

Discussion