Generalized Prompt Tuning: Adapting Frozen Univariate Time Series Foundation Models for Multivariate Healthcare Time Series
This addresses the challenge of applying time series foundation models to medical applications with scarce labeled data, though it is incremental as it builds on existing prompt-tuning techniques.
The paper tackled the problem of adapting univariate time series foundation models to handle multivariate healthcare time series, proposing Generalized Prompt Tuning (Gen-P-Tuning) to combine information across channels, and demonstrated effectiveness on MIMIC classification tasks and influenza-like illness forecasting.
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.