Information Templates: A New Paradigm for Intelligent Active Feature Acquisition

TL;DR

This paper introduces TAFA, a novel framework for active feature acquisition that learns feature templates to efficiently select informative features, reducing costs and improving performance over existing methods.

Contribution

The paper proposes a non-greedy, template-based approach for active feature acquisition that simplifies decision-making and removes the need for data distribution estimation.

Findings

TAFA outperforms state-of-the-art baselines in synthetic and real-world datasets.

It achieves lower acquisition costs and computational efficiency.

The framework effectively identifies joint informative feature templates.

Abstract

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.