SWIFT:面向时间序列基础模型预测的样本级实例微调框架
SWIFT: Sample-Wise Instance Fine-Tuning of Time-Series Foundation Models for Forecasting
AI 导读
SWIFT 是一种样本级实例微调框架,针对时间序列基础模型(TSFM),仅利用单个预测样本自身的历史数据实现细粒度微调,无需额外数据集。它结合 Self-Retrieval 历史挖掘、Frequency-Aware Loss 和 Deviation-Aware Dynamic Fusion。
正文 · 原文
Abstract:While current few-shot adaptation strategies for time series forecasting foundation models are predominantly dataset-centric, the necessity of obtaining an additional dataset for the finetuning process poses a significant hurdle for adoption. To address this constraint, we propose Sample-Wise Instance Fine-Tuning (SWIFT), a novel forecasting adaptation framework that achieves fine-grained specialization by leveraging structural priors from the target instance's own history. This shift allows the fine-tuning process to be entirely transparent to the end-user, which significantly enhances the ease of adoption. To implement this framework, SWIFT synergizes Self-Retrieval for historical mining and Frequency-Aware Loss for spectral consistency, while employing Deviation-Aware Dynamic Fusion to balance adaptation with general knowledge preservation. Extensive experiments across four TSFM backbones and three long-history benchmark subsets validate SWIFT, yielding average MASE and WQL reductions of 6.41% and 4.83% across 24 combinations of four backbones and six Chronos Benchmark II datasets. To the best of our knowledge, SWIFT is the first framework to investigate sample-wise instance fine-tuning of time-series foundation models, specializing the model for an individual prediction window using only the corresponding forecasting sample's own observed history.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.17915 [cs.AI] |
| (or arXiv:2611.17915v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17915 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Chen [view email]
[v1]
Fri, 13 Nov 2026 08:56:51 UTC (289 KB)
来源:arXiv cs.AI · arxiv.org