Lightweight Online Adaption for Time Series Foundation Model Forecasts
🤖 AI Summary
To address the challenge of online adaptation to dynamic data distributions after deployment of time-series foundation models, this paper proposes AdapTS, a lightweight online adaptation framework. Methodologically, AdapTS decouples foundation model inference from adapter learning via two novel modules: AdapTS-Forecaster—a linear or MLP-based lightweight time-series modeling component—and AdapTS-Weighter—a gradient-free, dynamically weighted fusion mechanism. It further incorporates online distribution estimation and real-time feedback-driven calibration. Crucially, AdapTS enables zero-shot fine-tuning and low-overhead adaptation without modifying the frozen foundation model. Evaluated across multiple standard benchmarks, AdapTS consistently improves the average MSE of mainstream time-series foundation models by 7.2%–15.8%, while incurring less than 3 ms additional inference latency. This demonstrates substantial gains in both predictive accuracy and practical deployability.
Application Category
📝 Abstract
Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs fail to adapt their forecasts to current data characteristics, despite the availability of online feedback from newly arriving data. This raises the question of whether FM performance can be enhanced by the efficient usage of this feedback. We propose AdapTS to answer this question. AdapTS is a lightweight mechanism for the online adaption of FM forecasts in response to online feedback. AdapTS consists of two parts: a) the AdapTS-Forecaster which is used to learn the current data distribution; and b) the AdapTS-Weighter which is used to combine the forecasts of the FM and the AdapTS-Forecaster. We evaluate the performance of AdapTS in conjunction with several recent FMs across a suite of standard time series datasets. In all of our experiments we find that using AdapTS improves performance. This work demonstrates how efficient usage of online feedback can be used to improve FM forecasts.
Problem
Research questions and friction points this paper is trying to address.
Enhance FM forecasts via online feedback
Lightweight online adaption for time series
AdapTS mechanism improves FM performance
Innovation
Methods, ideas, or system contributions that make the work stand out.
Lightweight online adaptation mechanism
Combines forecasts with current data
Improves foundation model performance
🔎 Similar Papers
No similar papers found.
