AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
This addresses the challenge of distribution shifts in time series forecasting for domains like finance or climate, though it is incremental as it builds on existing TTA and Neural ODE methods.
The paper tackles the problem of adapting pre-trained models to new data distributions for time series forecasting by proposing AdaNODEs, a test time adaptation method using Neural ODEs, which achieves relative improvements of 5.88% and 28.4% over state-of-the-art baselines.
Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA methods are designed for independent data, often overlooking the time series data and rarely addressing forecasting tasks. This paper presents AdaNODEs, an innovative source-free TTA method tailored explicitly for time series forecasting. By leveraging Neural Ordinary Differential Equations (NODEs), we propose a novel adaptation framework that accommodates the unique characteristics of distribution shifts in time series data. Moreover, we innovatively propose a new loss function to tackle TTA for forecasting tasks. AdaNODEs only requires updating limited model parameters, showing effectiveness in capturing temporal dependencies while avoiding significant memory usage. Extensive experiments with one- and high-dimensional data demonstrate that AdaNODEs offer relative improvements of 5.88\% and 28.4\% over the SOTA baselines, especially demonstrating robustness across higher severity distribution shifts.