Vision-Enhanced Time Series Forecasting via Latent Diffusion Models
This work addresses a problem in time series forecasting for researchers and practitioners by offering an incremental improvement through a novel cross-modal approach.
The paper tackles the challenge of effectively using visual representations for time series forecasting by proposing LDM4TS, a framework that converts time series into multi-view images and uses latent diffusion models for reconstruction, resulting in performance that outperforms specialized forecasting models.
Diffusion models have recently emerged as powerful frameworks for generating high-quality images. While recent studies have explored their application to time series forecasting, these approaches face significant challenges in cross-modal modeling and transforming visual information effectively to capture temporal patterns. In this paper, we propose LDM4TS, a novel framework that leverages the powerful image reconstruction capabilities of latent diffusion models for vision-enhanced time series forecasting. Instead of introducing external visual data, we are the first to use complementary transformation techniques to convert time series into multi-view visual representations, allowing the model to exploit the rich feature extraction capabilities of the pre-trained vision encoder. Subsequently, these representations are reconstructed using a latent diffusion model with a cross-modal conditioning mechanism as well as a fusion module. Experimental results demonstrate that LDM4TS outperforms various specialized forecasting models for time series forecasting tasks.