Saved in:
Bibliographic Details
Main Authors: Khosravani, Mohamadsadegh, Zilles, Sandra
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.02609
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909047581573120
author Khosravani, Mohamadsadegh
Zilles, Sandra
author_facet Khosravani, Mohamadsadegh
Zilles, Sandra
contents The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subsequently queried. This paper proposes a novel gradient-based acquisition criterion, derived from a generalization bound introduced by Luo et al. (2022). This criterion can be applied in lieu of uncertainty measures in uncertainty sampling, or incorporated into diversity-based methods that consider the spread of sampled points in addition to the uncertainty of their labels. We provide a theoretical justification of the proposed acquisition criterion, and demonstrate its effectiveness in an empirical evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02609
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gradient-Discrepancy Acquisition for Pool-Based Active Learning
Khosravani, Mohamadsadegh
Zilles, Sandra
Machine Learning
The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subsequently queried. This paper proposes a novel gradient-based acquisition criterion, derived from a generalization bound introduced by Luo et al. (2022). This criterion can be applied in lieu of uncertainty measures in uncertainty sampling, or incorporated into diversity-based methods that consider the spread of sampled points in addition to the uncertainty of their labels. We provide a theoretical justification of the proposed acquisition criterion, and demonstrate its effectiveness in an empirical evaluation.
title Gradient-Discrepancy Acquisition for Pool-Based Active Learning
topic Machine Learning
url https://arxiv.org/abs/2605.02609