arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.16433cs.LG
收藏

ECHO:利用历史相似案例与误差修正时间序列基础模型的预测

ECHO: Correcting Time Series Foundation Model Forecasts with Historical Analogues and Errors

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)

Boya Zhang, Xilin Dai, Yilin Wang, Qiang Xu, Luyao Dong, Xing He, Wen Wu

AI总结:

ECHO是一种黑盒预测修正框架,结合历史相似案例与误差信息,在5种TSFMs和9个数据集上使宏观平均MSE平均降低9.26%,且适用于长程预测。

摘要:

时间序列基础模型(TSFMs)具备通用预测能力,但其预测结果可能仍与目标领域的时间特征不匹配。这促使我们在仅能获取TSFM黑盒访问权限的情况下,开展轻量级预测修正工作。我们的核心发现是,两类历史信息可提供互补的修正信号:历史相似案例能揭示相似上下文的演变过程,而过往预测误差则能反映TSFM在目标领域的特征性偏差。基于该发现,我们提出了ECHO,这是一种从两类信息源学习的黑盒预测修正框架。ECHO使用AnalogE评估检索到的历史相似案例、当前上下文及基础预测,通过跨域预训练学习可迁移的修正;同时,RecentE从过往预测误差中学习目标特定的残差修正,并随着因果可用反馈的积累对其进行优化。ECHO会根据两类修正的观测预测性能动态组合它们。在5种代表性TSFMs和9个真实世界数据集上,ECHO在全部45种骨干模型-数据集设置中均降低了均方误差(MSE),宏观平均MSE的平均相对降低幅度达9.26%,其增益还延伸至长程预测场景。

英文摘要:

Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal characteristics of a target domain. This motivates lightweight forecast correction even when only black-box access to the TSFM is available. Our key observation is that two forms of historical information provide complementary correction signals: historical analogues reveal how similar contexts evolved, while past forecast errors reveal a TSFM's characteristic deviations in the target domain. Based on this observation, we propose ECHO, a black-box forecast correction framework that learns from both sources. ECHO uses AnalogE to assess retrieved historical analogues together with the current context and base forecast, learning transferable corrections through cross-domain pretraining. In parallel, RecentE learns target-specific residual corrections from past forecast errors and refines them as causally available feedback accumulates. ECHO dynamically combines the two corrections according to their observed forecasting performance. Across 5 representative TSFMs and 9 real-world datasets, ECHO reduces MSE in all 45 backbone--dataset settings, yielding an average relative reduction of 9.26\% in macro-average MSE. Its gains also extend to long-horizon forecasting.

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。

↑