Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at inference time, a policy sequentially chooses which features to acquire (at a cost) before predicting. Existing approaches either train reinforcement learning policies, which deal with a difficult MDP, or greedy policies that cannot account for the joint informativeness of features or require knowledge about the underlying data distribution. To overcome this, we propose Template-based AFA (TAFA), a non-greedy framework that learns a small library of feature templates -- sets of features that are jointly informative -- and uses this library of templates to guide the next feature acquisitions. Through identifying feature templates, the proposed framework not only significantly reduces the action space considered by the policy but also alleviates the need to estimate the underlying data distribution. Extensive experiments on synthetic and real-world datasets show that TAFA outperforms the existing state-of-the-art baselines while achieving lower overall acquisition cost and computation.

翻译：主动特征获取（AFA）是一种实例自适应的范式，在推理时，策略在预测前按顺序选择（以一定成本）获取哪些特征。现有方法要么训练处理复杂马尔可夫决策过程的强化学习策略，要么采用无法考虑特征联合信息性或需要底层数据分布知识的贪婪策略。为克服这些局限，我们提出基于模板的AFA（TAFA），这是一种非贪婪框架，通过学习小型特征模板库——即具有联合信息性的特征集合——并利用该模板库指导后续特征获取。通过识别特征模板，所提框架不仅显著缩减了策略需考虑的动作空间，还降低了对底层数据分布进行估计的需求。在合成数据集和真实数据集上的大量实验表明，TAFA在降低总体获取成本与计算量的同时，性能优于现有的先进基线方法。