Saved in:
Bibliographic Details
Main Authors: Norcliffe, Alexander, Lee, Changhee, Imrie, Fergus, van der Schaar, Mihaela, Lio, Pietro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480055541760
author Norcliffe, Alexander
Lee, Changhee
Imrie, Fergus
van der Schaar, Mihaela
Lio, Pietro
author_facet Norcliffe, Alexander
Lee, Changhee
Imrie, Fergus
van der Schaar, Mihaela
Lio, Pietro
contents Active Feature Acquisition is an instance-wise, sequential decision making problem. The aim is to dynamically select which feature to measure based on current observations, independently for each test instance. Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic acquisitions. To address these shortcomings, we introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a stochastic latent space. Extensive evaluation on a large range of synthetic and real datasets demonstrates that our approach reliably outperforms a diverse set of baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01957
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic Encodings for Active Feature Acquisition
Norcliffe, Alexander
Lee, Changhee
Imrie, Fergus
van der Schaar, Mihaela
Lio, Pietro
Machine Learning
Active Feature Acquisition is an instance-wise, sequential decision making problem. The aim is to dynamically select which feature to measure based on current observations, independently for each test instance. Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic acquisitions. To address these shortcomings, we introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a stochastic latent space. Extensive evaluation on a large range of synthetic and real datasets demonstrates that our approach reliably outperforms a diverse set of baselines.
title Stochastic Encodings for Active Feature Acquisition
topic Machine Learning
url https://arxiv.org/abs/2508.01957