表格基础模型的主动上下文学习：何时、何地、如何选标注样本
When, Where, How: Active In-Context Learning for Tabular Foundation Models
AI 导读
一项 arXiv 研究将主动学习获取规则引入表格基础模型（TFM）的上下文学习，提出 TANN 目标感知最近邻规则与 EPIC（上下文期望预测信息增益）方法，并在 20 个基准上对比多样性、不确定性与经典规则。
正文 · 原文
Abstract:Tabular Foundation Models (TFMs) adapt to a new task only through the labeled rows in their context. However, labels are expensive to acquire in real-world scenarios due to the need for highly specific domain knowledge to ensure high-quality data. Active in-context learning transfers classical acquisition rules to this setting, in which the model that guides acquisition changes with every label added. We ask how the value of diversity, predictive uncertainty and target-aware information gain changes as a frozen TFM acquires more context. For that, we study Target-Aware Nearest Neighbor (TANN) acquisition and the Expected Predictive Information Gain in Context (EPIC) and evaluate them against classical rules. Our study across twenty benchmarks with two well-established TFMs and classical GBDTs highlights three findings: (i) When: diversity-based acquisition is best during the first acquisition iterations; (ii) Where: labeling pool rows that serve the target inputs via a simple target-aware nearest-neighbor rule matters substantially; (iii) How: EPIC yields the best models at the label budget, retains on average 80--87% of the chance-corrected full-data performance with only 5-10% of the pool labeled on the eight benchmarks with the largest pools, and selects labels that also improve the predictive performance of gradient-boosted decision trees.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07886 [cs.LG] |
| (or arXiv:2611.07886v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07886 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Christian Frey [view email]
[v1]
Thu, 5 Nov 2026 12:04:48 UTC (397 KB)
来源：arXiv cs.AI · arxiv.org