Deep Individual Active Learning: Safeguarding against Out-of-Distribution Challenges in Neural Networks

Author:

Shayovitz Shachar1ORCID,Bibas Koby1,Feder Meir1

Affiliation:

1. School of Electrical Engineering, Tel Aviv University, Tel Aviv 6997801, Israel

Abstract

Active learning (AL) is a paradigm focused on purposefully selecting training data to enhance a model’s performance by minimizing the need for annotated samples. Typically, strategies assume that the training pool shares the same distribution as the test set, which is not always valid in privacy-sensitive applications where annotating user data is challenging. In this study, we operate within an individual setting and leverage an active learning criterion which selects data points for labeling based on minimizing the min-max regret on a small unlabeled test set sample. Our key contribution lies in the development of an efficient algorithm, addressing the challenging computational complexity associated with approximating this criterion for neural networks. Notably, our results show that, especially in the presence of out-of-distribution data, the proposed algorithm substantially reduces the required training set size by up to 15.4%, 11%, and 35.1% for CIFAR10, EMNIST, and MNIST datasets, respectively.

Publisher

MDPI AG

Reference51 articles.

1. A survey of deep active learning;Ren;ACM Comput. Surv. (CSUR),2021

2. Cost-effective active learning for deep image classification;Wang;IEEE Trans. Circuits Syst. Video Technol.,2016

3. Houlsby, N., Huszár, F., Ghahramani, Z., and Lengyel, M. (2011). Bayesian active learning for classification and preference learning. arXiv.

4. Gal, Y., Islam, R., and Ghahramani, Z. (2017, January 6–11). Deep bayesian active learning with image data. Proceedings of the International Conference on Machine Learning, Sydney, Australia.

5. Sener, O., and Savarese, S. (May, January 30). Active Learning for Convolutional Neural Networks: A Core-Set Approach. Proceedings of the International Conferenc on Learning Representations, Vancouver, BC, Canada.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3