Generalized Prompt Tuning: Adapting Frozen Univariate Time Series Foundation Models for Multivariate Healthcare Time Series

TL;DR

This paper introduces Generalized Prompt Tuning, a method to adapt univariate time series foundation models for multivariate healthcare data, improving their ability to model inter-variable relationships with limited labeled data.

Contribution

The paper proposes a novel prompt-tuning technique that enables existing univariate models to effectively handle multivariate time series in healthcare applications.

Findings

Effective in MIMIC classification tasks

Improves influenza-like illness forecasting

Outperforms baseline methods

Abstract

Time series foundation models are pre-trained on large datasets and are able to achieve state-of-the-art performance in diverse tasks. However, to date, there has been limited work demonstrating how well these models perform in medical applications, where labeled data can be scarce. Further, we observe that currently, the majority of time series foundation models either are univariate in nature, or assume channel independence, meaning that they handle multivariate time series but do not model how the different variables relate. In this paper, we propose a prompt-tuning-inspired fine-tuning technique, Generalized Prompt Tuning (Gen-P-Tuning), that enables us to adapt an existing univariate time series foundation model (treated as frozen) to handle multivariate time series prediction. Our approach provides a way to combine information across channels (variables) of multivariate time series. We demonstrate the effectiveness of our fine-tuning approach against various baselines on two MIMIC classification tasks, and on influenza-like illness forecasting.