arXiv：cs.LG· Yuta Kobayashi, Divyam Madaan, Shalmali Joshi·· 4 小时前AI 评分32
用表格基础模型评估主动特征获取策略
Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models
AI 导读
研究用先验数据拟合网络（PFN）从有限离线数据中学习和评估主动特征获取策略。作者发现离线数据覆盖不均衡时，以总预测熵为奖励会引入认知偏差，惩罚对稀疏观测特征的获取，因为该奖励混淆了认知不确定性与偶然不确定性；改用后验期望（偶然）熵评估特征获取，在合成和真实数据集上一致降低了价值估计偏差，并给出经验覆盖率较高的可信区间，可改善下游策略选择。
正文
Abstract:Active feature acquisition learns policies that sequentially acquire features to maximize information about a target variable. We study how to learn and evaluate such policies from finite offline data using prior-data fitted networks (PFNs), which are off-the-shelf models that output posterior predictive distributions without task-specific training. We show that under the imbalanced coverage of offline data, using total predictive entropy as a reward creates an epistemic bias that penalizes acquiring sparsely observed features. Specifically, this reward conflates epistemic uncertainty (arising from lack of offline data) with aleatoric uncertainty (arising from uninformative features). To address this, we target the posterior expected (aleatoric) entropy instead of the total predictive entropy output by a PFN for evaluating feature acquisitions. Empirical evaluations on synthetic and real-world datasets demonstrate that our approach consistently reduces value estimation bias and yields credible intervals with strong empirical coverage, which can translate to improved downstream policy selection.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07406 [cs.LG] |
| (or arXiv:2610.07406v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07406 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuta Kobayashi [view email]
[v1]
Mon, 5 Oct 2026 21:16:50 UTC (737 KB)
来源：arXiv：cs.LG · arxiv.org