Multi-Modal Time Series Prediction via Mixture of Modulated Experts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Lige, Maatouk, Ali, Chen, Jialin, Tassiulas, Leandros, Ying, Rex
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911406290370560
author Zhang, Lige
Maatouk, Ali
Chen, Jialin
Tassiulas, Leandros
Ying, Rex
author_facet Zhang, Lige
Maatouk, Ali
Chen, Jialin
Tassiulas, Leandros
Ying, Rex
contents Real-world time series exhibit complex and evolving dynamics, making accurate forecasting extremely challenging. Recent multi-modal forecasting methods leverage textual information such as news reports to improve prediction, but most rely on token-level fusion that mixes temporal patches with language tokens in a shared embedding space. However, such fusion can be ill-suited when high-quality time-text pairs are scarce and when time series exhibit substantial variation in scale and characteristics, thus complicating cross-modal alignment. In parallel, Mixture-of-Experts (MoE) architectures have proven effective for both time series modeling and multi-modal learning, yet many existing MoE-based modality integration methods still depend on token-level fusion. To address this, we propose Expert Modulation, a new paradigm for multi-modal time series prediction that conditions both routing and expert computation on textual signals, enabling direct and efficient cross-modal control over expert behavior. Through comprehensive theoretical analysis and experiments, our proposed method demonstrates substantial improvements in multi-modal time series prediction. The current code is available at https://github.com/BruceZhangReve/MoME
format Preprint
id arxiv_https___arxiv_org_abs_2601_21547
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Modal Time Series Prediction via Mixture of Modulated Experts
Zhang, Lige
Maatouk, Ali
Chen, Jialin
Tassiulas, Leandros
Ying, Rex
Machine Learning
Artificial Intelligence
Real-world time series exhibit complex and evolving dynamics, making accurate forecasting extremely challenging. Recent multi-modal forecasting methods leverage textual information such as news reports to improve prediction, but most rely on token-level fusion that mixes temporal patches with language tokens in a shared embedding space. However, such fusion can be ill-suited when high-quality time-text pairs are scarce and when time series exhibit substantial variation in scale and characteristics, thus complicating cross-modal alignment. In parallel, Mixture-of-Experts (MoE) architectures have proven effective for both time series modeling and multi-modal learning, yet many existing MoE-based modality integration methods still depend on token-level fusion. To address this, we propose Expert Modulation, a new paradigm for multi-modal time series prediction that conditions both routing and expert computation on textual signals, enabling direct and efficient cross-modal control over expert behavior. Through comprehensive theoretical analysis and experiments, our proposed method demonstrates substantial improvements in multi-modal time series prediction. The current code is available at https://github.com/BruceZhangReve/MoME
title Multi-Modal Time Series Prediction via Mixture of Modulated Experts
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.21547