发表机构
University of São Paulo (USP)（圣保罗大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TS2TabPFN框架将显式特征提取与表格基础模型TabPFN 2.5集成，在时间序列外生回归任务中显著优于现有最优模型，为时间序列分类提供了稳健高效的替代方案，建立了新的时间序列最优水平。
AI 中文摘要
时间序列数据在实际应用中无处不在，分类（TSC）和外生回归（TSER）已成为从时间序列中获取价值的核心任务。尽管相关文献中基于特征的模型和深度学习模型已取得显著进展，但现有方法通常要么关注特征提取的质量，要么关注应用于原始数据的复杂架构的内在预测能力。这种划分在特征工程提供的可控性与端到端模型的自动化性能之间造成了差距。本文提出了TS2TabPFN，该框架通过将显式特征提取与表格数据的前沿基础模型TabPFN 2.5相集成，以利用其预测能力，从而弥合这一差距。我们的广泛实验评估表明，TS2TabPFN在TSER任务中以统计显著性显著优于现有最先进模型，为TSC提供了一种稳健且高效的替代方案，并且超越了大多数当前性能最佳的算法。这些结果表明，将基础模型与结构化特征相结合可克服单一范式的局限性，建立了新的时间序列最先进水平。
英文摘要
Time series data are ubiquitous in practical applications, where classification (TSC) and extrinsic regression (TSER) have emerged as essential tasks for obtaining value from temporal sequences. While the literature has seen significant progress through feature-based and deep learning models, existing methods often focus either on the quality of feature extraction or on the intrinsic predictive power of complex architectures applied to raw data. This division creates a gap between the control offered by feature engineering and the automated performance of end-to-end models. This paper proposes TS2TabPFN, a framework that bridges this gap by integrating explicit feature extraction with TabPFN 2.5, a cutting-edge foundation model for tabular data, to leverage its predictive capabilities. Our extensive experimental evaluation demonstrates that TS2TabPFN significantly outperforms state-of-the-art models in TSER tasks with statistical significance, providing a robust and efficient alternative for TSC and surpassing most of the currently best-performing algorithms. These results suggest that combining foundation models with structured features overcomes single-paradigm limitations, establishing a new time series state-of-the-art.
CommentsAccepted at ECML PKDD 2026. To appear in Springer LNCS. 18 pages; 7 figures
Journal refMachine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2026. Lecture Notes in Computer Science, vol. 16947. Springer, Cham, 2027
DOI：10.1007/978-3-032-37676-3_32
