paper-with-me

홈 › Papers

Gradient-Discrepancy Acquisition for Pool-Based Active Learning

2026-05-04 · Mohamadsadegh Khosravani, Sandra Zilles arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.02609

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Efficient Active Learning for Gaussian Process Classification by Error Reduction

2021-12-01 · NeurIPS 2021 12 · Guang Zhao, Edward Dougherty, Byung-Jun Yoon, Francis Alexander 외

Active learning sequentially selects the best instance for labeling by optimizing an acquisition function to enhance data/label efficiency. The selection can be either from a discrete instance set (pool-based scenario) o…

Active LearningClassificationComputational Efficiency

Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers

2021-06-22 · Andreas Kirsch, Tom Rainforth, Yarin Gal

Expanding on MacKay (1992), we argue that conventional model-based methods for active learning - like BALD - have a fundamental shortfall: they fail to directly account for the test-time distribution of the input variabl…

Active Learning

MCDAL: Maximum Classifier Discrepancy for Active Learning

2021-07-23 · Jae Won Cho, Dong-Jin Kim, Yunjae Jung, In So Kweon

Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parame…

Active LearningClassificationDomain Adaptationimage-classification+2

Pool-based sequential active learning with multi kernels

2020-10-22 · Jeongmin Chae, SongNam Hong

We study a pool-based sequential active learning (AL), in which one sample is queried at each time from a large pool of unlabeled data according to a selection criterion. For this framework, we propose two selection crit…

Active Learning

Active Learning from the Web

2022-10-15 · Ryoma Sato

Labeling data is one of the most costly processes in machine learning pipelines. Active learning is a standard approach to alleviating this problem. Pool-based active learning first builds a pool of unlabelled data and i…

Active LearningInformation RetrievalRetrieval