[论文] Active Feature Acquisition by Distilling an Oracle Teacher
论文概要
研究领域: ML
作者: Yang Meng, Zixin Ding, Robert L. Grossman, Yuxin Chen
发布时间: 2026-11-19
arXiv: 2611.26598
中文摘要
获取实例的每个特征往往代价高昂:测量可能带有金钱价格、时间延迟或隐私成本。主动特征获取(AFA)通过学习一个策略来解决此问题,该策略针对每个实例决定在给定预算下获取哪些特征。现有AFA方法通过优化自构建的效用目标而非蒸馏显式教师来训练策略。我们显式构建教师:训练时标签和未观测特征值可用,二者共同以闭式解确定教师——一个按每个候选特征对下游预测器误差影响排序的预言机。OracleImitator通过软目标模仿将此排序蒸馏为可部署策略。在多模态医学诊断和AFABench基准上,OracleImitator在预算范围内匹配或超越现有AFA方法,以不到四分之一的获取成本恢复90%的可达准确率增益。由于教师是显式算法对象而非隐式优化目标,我们还能直接测量其排序中有多少比例可被限制于部署时可见信息的策略恢复。
原文摘要
Acquiring every feature of an instance is often costly: a measurement can carry a monetary price, a time delay, or a privacy cost. Active Feature Acquisition (AFA) addresses this by learning a policy that decides, per instance, which features to acquire under a budget. Existing AFA methods train this policy by optimizing a self-constructed utility target rather than distilling an explicit teacher. We construct this teacher explicitly. At training time the label and the unobserved feature values are available, and together they determine the teacher in closed form: an oracle that ranks every candidate by its effect on the downstream predictor's error. OracleImitator distills this ranking into a deployable policy by soft-target imitation. Across multimodal medical diagnosis and the AFABench ...
自动采集于 2026-11-21
#论文 #arXiv #ML #小凯