paper-with-me

Papers

Batch Active Learning from the Perspective of Sparse Approximation

2022-11-01 · Maohao Shen, Bowen Jiang, Jacky Yibo Zhang, Oluwasanmi Koyejo

Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's perspective. Our active learning method aims to find an informative subset from the unlabeled data pool such that the corresponding training loss function approximates its full data pool counterpart. We realize the framework as sparsity-constrained discontinuous optimization problems, which explicitly balance uncertainty and representation for large-scale applications and could be solved by greedy or proximal iterative hard thresholding algorithms. The proposed method can adapt to various settings, including both Bayesian and non-Bayesian neural networks. Numerical experiments show that our work achieves competitive performance across different settings with lower computational complexity.

📄 PDF Abstract BibTeX arXiv:2211.00246

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

SABAL: Sparse Approximation-based Batch Active Learning

2021-09-29 · Maohao Shen, Bowen Jiang, Jacky Y. Zhang, Oluwasanmi O Koyejo

We propose a novel and general framework (i.e., SABAL) that formulates batch active learning as a sparse approximation problem. SABAL aims to find a weighted subset from the unlabeled data pool such that the correspondin…

Active Learning

Bayesian Batch Active Learning as Sparse Subset Approximation

2019-08-06 · NeurIPS 2019 12 · Robert Pinsler, Jonathan Gordon, Eric Nalisnick, José Miguel Hernández-Lobato

Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to g…

Active Learning

Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning

2023-01-23 · Andreas Kirsch

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesian neural networks to find the most info…

Active Learning

Impact of Batch Size on Stopping Active Learning for Text Classification

2018-01-24 · Garrett Beatty, Ethan Kochis, Michael Bloodgood

When using active learning, smaller batch sizes are typically more efficient from a learning efficiency perspective. However, in practice due to speed and human annotator considerations, the use of larger batch sizes is …

Active LearningGeneral ClassificationOpen-Ended Question Answeringtext-classification+1

BatchGFN: Generative Flow Networks for Batch Active Learning

2023-06-26 · Shreshth A. Malik, Salem Lahlou, Andrew Jesson, Moksh Jain 외

We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an appropriate reward function to quantify th…

Active Learning