Gradient-Discrepancy Acquisition for Pool-Based Active 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Efficient Active Learning for Gaussian Process Classification by Error Reduction
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 EfficiencyTest Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
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 LearningMCDAL: Maximum Classifier Discrepancy for Active Learning
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+2Pool-based sequential active learning with multi kernels
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 LearningActive Learning from the Web
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