AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs

TL;DR

AdaNODEs introduces a test time adaptation method using Neural ODEs specifically designed for time series forecasting, effectively handling distribution shifts with limited parameter updates and demonstrating significant performance improvements.

Contribution

The paper proposes AdaNODEs, a novel source-free TTA framework utilizing Neural ODEs tailored for time series forecasting, addressing distribution shifts effectively.

Findings

Achieves up to 28.4% improvement over SOTA baselines.

Effectively captures temporal dependencies with limited parameter updates.

Demonstrates robustness across high-severity distribution shifts.

Abstract

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.