arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.00487cs.LGcs.AI
收藏

基于跨提示基础模型的黑盒时间序列域自适应

Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models

STEM, University of South Australia(南澳大利亚大学STEM学院);Faculty of Electrical and Computer Engineering, University of Ljubljana(卢布尔雅那大学电气与计算机工程学院)

M. T. Furqon, Mahardhika Pratama, Igor Skrjanc, Lin Liu, Habibullah Habibullah, Kutluyil Dogancay

AI总结:

针对现有黑盒域自适应方法难适配时间序列场景、未利用基础模型的问题,提出基于双分支跨提示结构、搭配重构学习的时间序列黑盒域自适应方法CPFM,在三个不同领域数据集上以显著优势超越对比方法。

摘要:

黑盒域自适应(BBDA)研究方向旨在解决仅能通过源模型的应用程序编程接口(API)开展域自适应时的隐私与安全问题。尽管BBDA已吸引越来越多的研究关注,但现有工作大多针对视觉应用,无法直接应用于具备独特时空特性的时间序列场景。此外,现有方法均未探索基础模型在黑盒时间序列域自适应(BBTSDA)中的潜力。本文针对BBTSDA问题提出了跨提示基础模型(CPFM)的概念。CPFM采用双分支网络结构构建,每个分支配备专属提示以捕捉数据分布的不同特征;在域自适应阶段,设计了提示层面与输入层面的重构学习机制,所有模块均基于时间序列基础模型搭建,以应对时空动态性。我们的严格实验证实了CPFM的优势:在三个不同应用领域的时间序列数据集上,CPFM以显著幅度优于所有对比方法,取得了更优的结果。

英文摘要:

The black-box domain adaptation (BBDA) topic is developed to address the privacy and security issues where only an application programming interface (API) of the source model is available for domain adaptations. Although the BBDA topic has attracted growing research attentions, existing works mostly target the vision applications and are not directly applicable to the time-series applications possessing unique spatio-temporal characteristics. In addition, none of existing approaches have explored the strength of foundation model for black box time-series domain adaptation (BBTSDA). This paper proposes a concept of Cross-Prompt Foundation Model (CPFM) for the BBTSDA problems. CPFM is constructed under a dual branch network structure where each branch is equipped with a unique prompt to capture different characteristics of data distributions. In the domain adaptation phase, the reconstruction learning phase in the prompt and input levels is developed. All of which are built upon a time-series foundation model to overcome the spatio-temporal dynamic. Our rigorous experiments substantiate the advantage of CPFM achieving improved results with noticeable margins from its competitors in three time-series datasets of different application domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑