Pre-Training Acquisition Functions by Deep Reinforcement Learning for Fixed Budget Active Learning
Pre-Training Acquisition Functions by Deep Reinforcement Learning for Fixed Budget Active Learning
复制标题
DOI：
10.1007/s11063-021-10476-z
复制
发表时间：
2021-03
影响因子：
3.1
通讯作者：
Yusuke Taguchi;H. Hino;K. Kameyama
中科院分区：
文献类型：
--
作者：
Yusuke Taguchi;H. Hino;K. Kameyama
在监督学习中，有许多情况下数据的获取非常昂贵，有时由用户的预算决定。解决这一局限性的一种方法是主动学习。在这项研究中，我们专注于一个固定的预算制度，并提出了一种新的主动学习算法的池为基础的主动学习问题。所提出的方法执行主动学习与预先训练的采集功能，以便可以获得的数据的数量是固定的时，可以实现最大的性能。为了实现这种主动学习算法，所提出的方法使用基于深度神经网络的强化学习作为针对固定预算情况定制的预训练获取函数。通过使用预先训练的基于深度Q学习的采集函数，我们可以实现主动学习器，该主动学习器考虑到固定预算的情况从未标记样本池中选择用于注释的样本。实验结果表明，该方法与现有的主动学习方法相当或上级，表明了该方法在固定预算主动学习中的有效性.
There are many situations in supervised learning where the acquisition of data is very expensive and sometimes determined by a user’s budget. One way to address this limitation is active learning. In this study, we focus on a fixed budget regime and propose a novel active learning algorithm for the pool-based active learning problem. The proposed method performs active learning with a pre-trained acquisition function so that the maximum performance can be achieved when the number of data that can be acquired is fixed. To implement this active learning algorithm, the proposed method uses reinforcement learning based on deep neural networks as as a pre-trained acquisition function tailored for the fixed budget situation. By using the pre-trained deep Q-learning-based acquisition function, we can realize the active learner which selects a sample for annotation from the pool of unlabeled samples taking the fixed-budget situation into account. The proposed method is experimentally shown to be comparable with or superior to existing active learning methods, suggesting the effectiveness of the proposed approach for the fixed-budget active learning.