Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting

TL;DR

PETSA is a parameter-efficient test-time adaptation method for time series forecasting that updates small modules to improve accuracy without retraining the entire model, using a specialized loss to maintain performance.

Contribution

We introduce PETSA, a novel, parameter-efficient TTA approach that adapts forecasters with minimal updates and a specialized loss to enhance non-stationary time series forecasting.

Findings

PETSA achieves competitive or superior performance across benchmarks.

It requires fewer parameters than existing methods.

PETSA effectively maintains accuracy with limited adaptation capacity.

Abstract

Real-world time series often exhibit a non-stationary nature, degrading the performance of pre-trained forecasting models. Test-Time Adaptation (TTA) addresses this by adjusting models during inference, but existing methods typically update the full model, increasing memory and compute costs. We propose PETSA, a parameter-efficient method that adapts forecasters at test time by only updating small calibration modules on the input and output. PETSA uses low-rank adapters and dynamic gating to adjust representations without retraining. To maintain accuracy despite limited adaptation capacity, we introduce a specialized loss combining three components: (1) a robust term, (2) a frequency-domain term to preserve periodicity, and (3) a patch-wise structural term for structural alignment. PETSA improves the adaptability of various forecasting backbones while requiring fewer parameters than baselines. Experimental results on benchmark datasets show that PETSA achieves competitive or better performance across all horizons. Our code is available at: https://github.com/BorealisAI/PETSA