MUSE adapts frozen vision models for better forecasting of time series
MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting
Machine Learning
Summary
Forecasting multiple connected time-based signals is important but challenging. The authors designed MUSE, which uses a frozen large vision model to analyze time series as images without losing important relationships between signals. MUSE includes two parts that refine representations differently and combine their predictions for better accuracy. Tests on many real datasets showed MUSE achieves improved forecasting results compared to prior methods.
What this means in practice
- •For industrial forecasting teams: Generate more accurate forecasts from multiple correlated sensor readings by using pretrained vision models adapted with MUSE.
- •For energy grid operators: Improve demand and supply forecasts by modeling periodic and cross-variable temporal patterns in multivariate load data.
Authors
Xinying Cai, Junkai Lu, Yuhan Zhu, Xiaoyun Yu, Xiangfei Qiu, Jilin Hu
Abstract
Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by transferring cross-domain visual priors to time-series forecasting. However, existing LVM-based methods face two key challenges: balancing independent visual representation spaces with cross-variable dependency modeling, and adapting vision backbones pretrained on natural images to the distinct temporal semantics of time-series images. To address these challenges, we propose MUSE, a dependency-aware adaptation framework built on a fully frozen pretrained MAE. First, the Variable Context Refinement Module (VCR) aggregates shared temporal information within each variable and models cross-variable contextual dependencies while preserving independent visual spaces. Second, the Temporal-Periodic Refinement Module (TPR) performs lightweight refinement at different encoder depths and explicitly models across-period temporal dependencies and within-period periodic dependencies. The two modules independently produce forecasts, which are fused through a learnable prediction-level gate. Experiments on 10 real-world datasets demonstrate that MUSE achieves state-of-the-art performance.