Gradient-Discrepancy Acquisition for Pool-Based Active Learning

2026-05-04

AI Summary

This work addresses the insufficient informativeness of sample selection in active learning by proposing a novel acquisition criterion based on gradient discrepancy. Rooted in the generalization error bound established by Luo et al., this criterion is the first to integrate gradient discrepancy with theoretical generalization bounds, thereby providing a principled foundation for sample selection. The proposed method serves as a viable alternative to conventional uncertainty-based measures and naturally unifies label uncertainty and sample diversity, bridging two dominant active learning paradigms. Theoretical analysis corroborates its validity, and empirical results demonstrate that the criterion consistently outperforms existing active learning approaches across multiple benchmark datasets.

Abstract

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.

Problem

• active learning
• acquisition criterion
• gradient-based
• pool-based
• data selection

Innovation

• gradient-based acquisition
• active learning
• generalization bound
• uncertainty sampling
• diversity-based sampling