Estimating Time Series Foundation Model Transferability via In-Context Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Qingren, Jin, Ming, Zhang, Chengqi, Yang, Chao-Han Huck, Qi, Jun, Pan, Shirui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914061798604800
author Yao, Qingren
Jin, Ming
Zhang, Chengqi
Yang, Chao-Han Huck
Qi, Jun
Pan, Shirui
author_facet Yao, Qingren
Jin, Ming
Zhang, Chengqi
Yang, Chao-Han Huck
Qi, Jun
Pan, Shirui
contents Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs, efficiently identifying the best model for downstream fine-tuning becomes increasingly challenging. In this work, we introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem: given observations on known (source) datasets, it predicts how a TSFM will perform after fine-tuning on a downstream (target) dataset. TimeTic flexibly organizes the observed model-data relationships as contextual information, allowing it to adapt seamlessly to various test-time scenarios. Leveraging the natural tabular structure formed by dataset meta-features, model characteristics, and fine-tuned performance, we employ tabular foundation models to serve as in-context learners. We further introduce a novel model characterization based on entropy evolution across model layers, capturing embedding-space distinctions and enabling TimeTic to generalize across arbitrary model sets. We establish a comprehensive benchmark for transferability estimation including 10 datasets, 10 foundation models, and 3 forecasting tasks. On this benchmark, TimeTic's estimation demonstrates strong alignment with actual fine-tuned performance for previously unseen datasets, achieving a mean rank correlation of approximately 0.6 and a 30% improvement compared to using zero-shot performance as the transferability score.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating Time Series Foundation Model Transferability via In-Context Learning
Yao, Qingren
Jin, Ming
Zhang, Chengqi
Yang, Chao-Han Huck
Qi, Jun
Pan, Shirui
Machine Learning
Artificial Intelligence
Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs, efficiently identifying the best model for downstream fine-tuning becomes increasingly challenging. In this work, we introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem: given observations on known (source) datasets, it predicts how a TSFM will perform after fine-tuning on a downstream (target) dataset. TimeTic flexibly organizes the observed model-data relationships as contextual information, allowing it to adapt seamlessly to various test-time scenarios. Leveraging the natural tabular structure formed by dataset meta-features, model characteristics, and fine-tuned performance, we employ tabular foundation models to serve as in-context learners. We further introduce a novel model characterization based on entropy evolution across model layers, capturing embedding-space distinctions and enabling TimeTic to generalize across arbitrary model sets. We establish a comprehensive benchmark for transferability estimation including 10 datasets, 10 foundation models, and 3 forecasting tasks. On this benchmark, TimeTic's estimation demonstrates strong alignment with actual fine-tuned performance for previously unseen datasets, achieving a mean rank correlation of approximately 0.6 and a 30% improvement compared to using zero-shot performance as the transferability score.
title Estimating Time Series Foundation Model Transferability via In-Context Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.23695