arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.09856cs.LGstat.ML
收藏

基于丢弃的主动学习回归

Dropout-based Active Learning for Regression

Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术研究所(斯科尔科沃理工学院))

Evgenii Tsymbalov, Maxim Panov, Alexander Shapeev

摘要:

当样本的注释代价很高时,主动学习对于高维回归模型是相关的和具有挑战性的。然而现有的大多数抽样方法不能适用于大规模的问题,耗费太多的时间进行数据处理。在本文中,我们提出了一个快速的主动学习算法回归,适合神经网络模型。它是基于不确定性估计从随机辍学的网络输出。与基线相比,在合成和真实世界数据集上的实验显示出相当或更好的性能(取决于准确性度量)。这种方法可以推广到其他深度学习架构。它可以用来系统地改进机器学习模型,因为它提供了一种计算效率高的方法来采样额外的数据。

英文摘要:

Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time for data processing. In this paper, we propose a fast active learning algorithm for regression, tailored for neural network models. It is based on uncertainty estimation from stochastic dropout output of the network. Experiments on both synthetic and real-world datasets show comparable or better performance (depending on the accuracy metric) as compared to the baselines. This approach can be generalized to other deep learning architectures. It can be used to systematically improve a machine-learning model as it offers a computationally efficient way of sampling additional data.

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。

↑