发表机构
Colegio de Ciencias e Ingenierías, Universidad San Francisco de Quito (USFQ); Rey Juan Carlos University; Facultad de Ingeniería, Universidad Latina de Panamá（基多圣弗朗西斯科大学科学与工程学院; 胡安·卡洛斯国王大学; 巴拿马拉丁大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究对九种表格基础模型进行分布外性能实证评估，涵盖多种策略与架构，用三个真实世界数据集测试。结果显示模型在分布变化下会退化，还存在可扩展性差距，扩展了表格数据分布外的基准，为高风险领域应用提供证据。
AI 中文摘要
表格基础模型（TFMs）已成为表格预测任务的新方法，在独立同分布数据上训练和评估，但现实场景中的分布变化会影响其稳健性。本文对九种TFMs进行分布外（OOD）性能实证评估，涵盖多种预训练策略和架构，使用三个真实世界数据集。结果表明所有评估的TFMs在分布变化下都会系统退化，且存在可扩展性差距。该研究扩展了表格数据OOD的现有基准，为其在高风险领域的应用提供了证据。
英文摘要
Tabular Foundation Models (TFMs) have emerged as novel approaches for tabular predictive tasks, demonstrating competitive predictive performance to ensemble tree-based models. Most TFMs are trained and evaluated on independent and identically distributed data, but this assumption changes in real-world scenarios due to distribution shifts, which compromise the robustness of models. Limited research has been conducted of TFMs under distribution shifts. We present an empirical evaluation of Out-Of-Distribution (OOD) performance of nine TFMs, spanning diverse pre-training strategies and architectures: TabPFNv2, TabPFNv2.5, TabPFNv2.6, TabPFNv3, TabICL, TabICLv2, Mitra, LimiX and TabFM. Three real-world datasets from the TableShift study were considered (HELOC, Voting, Childhood Lead), covering label, socioeconomic, and geographic shift types. Our results show that all evaluated TFMs degrade systematically under distribution shift regardless of pre-training strategy, with shift gaps ranging from 0.003 to 0.060 depending on shift type. The relationship between in-distribution and OOD predictive performance documented for classical tabular models extends into TFMs. We also identified a scalability gap, as high-performing models demand significant memory and computational resources beyond what standard deployment infrastructure can support. This study extends existing benchmarks for OOD in tabular data, providing evidence to support their adoption in high-stakes domains characterized by structural distribution shifts.
