paper-with-me

홈 › Papers

Deep Active Learning: Unified and Principled Method for Query and Training

2019-11-20 · Changjian Shui, Fan Zhou, Christian Gagné, Boyu Wang

In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting the Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameters and batch query selection through alternative optimization. In addition, the loss for training a deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally, we evaluate our proposed method on different benchmarks, consistently showing better empirical performances and a better time-efficient query strategy compared to the baselines.

📄 PDF Abstract BibTeX arXiv:1911.09162

Code (1)

cjshui/WAAL 공식 구현 pytorch

Tasks

Active LearningDiversity

Similar Papers 제목 키워드 기반

Active Learning by Querying Informative and Representative Examples

2010-12-01 · NeurIPS 2010 12 · Sheng-Jun Huang, Rong Jin, Zhi-Hua Zhou

Most active learning approaches select either informative or representative unlabeled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criterions for quer…

Active LearningInformativeness

Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks

2020-09-22 · John Daniel Bossér, Erik Sörstadius, Morteza Haghir Chehreghani

We study different aspects of active learning with deep neural networks in a consistent and unified way. i) We investigate incremental and cumulative training modes which specify how the newly labeled data are used for t…

Active LearningInformativeness

Bounds on the Generalization Error in Active Learning

2024-09-10 · Vincent Menden, Yahya Saleh, Armin Iske

We establish empirical risk minimization principles for active learning by deriving a family of upper bounds on the generalization error. Aligning with empirical observations, the bounds suggest that superior query algor…

Active LearningInformativeness

Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions

2024-01-09 · Andreas Kirsch

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specificall…

Active LearningDeep Learning

Active Learning with Oracle Epiphany

2016-12-01 · NeurIPS 2016 12 · Tzu-Kuo Huang, Lihong Li, Ara Vartanian, Saleema Amershi 외

We present a theoretical analysis of active learning with more realistic interactions with human oracles. Previous empirical studies have shown oracles abstaining on difficult queries until accumulating enough informatio…

Active Learning