arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.04798cs.LGstat.ML
收藏

基于深度强化学习的元学习迁移主动学习策略

Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning

University of Edinburgh(爱丁堡大学);University College London(伦敦大学学院);Nara Institute of Science and Technology(奈良先端科学技术大学院大学)

Kunkun Pang, Mingzhi Dong, Yang Wu, Timothy Hospedales

摘要:

主动学习(AL)的目标是通过预测未标记实例的哪个子集最有利于标记来训练具有低标注成本的高性能分类器。人工智能的重要性激发了广泛的研究,提出了各种各样的人工设计的人工智能算法与不同的理论和直观的动机。与此相反,我们建议将主动学习算法设计视为一个元学习问题,并从数据中学习最佳标准。我们将主动学习算法建模为深度神经网络,该网络输入基本学习者状态和未标记的点集,并预测接下来要注释的最佳点。用强化学习训练这个主动查询策略网络,为给定的数据集产生最佳的非近视策略。实现AL的通用解决方案的关键挑战就变成了学习者的泛化,特别是在异构数据集之间。我们提出了一个多任务的嵌入式方法,允许嵌入式不可知的主动学习者进行培训。我们的评估表明,以这种方式训练的AL算法可以直接概括各种问题。

英文摘要:

Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research, proposing a wide variety of manually designed AL algorithms with diverse theoretical and intuitive motivations. In contrast to this body of research, we propose to treat active learning algorithm design as a meta-learning problem and learn the best criterion from data. We model an active learning algorithm as a deep neural network that inputs the base learner state and the unlabelled point set and predicts the best point to annotate next. Training this active query policy network with reinforcement learning, produces the best non-myopic policy for a given dataset. The key challenge in achieving a general solution to AL then becomes that of learner generalisation, particularly across heterogeneous datasets. We propose a multi-task dataset-embedding approach that allows dataset-agnostic active learners to be trained. Our evaluation shows that AL algorithms trained in this way can directly generalise across diverse problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑