Computationally Efficient Class-Prior Estimation under Class Balance Change Using Energy Distance
Computationally Efficient Class-Prior Estimation under Class Balance Change Using Energy Distance
复制标题
DOI：
10.1587/transinf.2015edp7212
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Hideko Kawakubo;M. C. D. Plessis;Masashi Sugiyama
中科院分区：
文献类型：
--
作者：
Hideko Kawakubo;M. C. D. Plessis;Masashi Sugiyama
在许多现实世界的分类问题中，由于样本选择偏差或环境的非平稳性，训练和测试数据集之间的类平衡经常发生变化。在这种类平衡的变化下，朴素的分类器训练系统地产生有偏差的解决方案。众所周知，这种系统偏差可以通过根据测试类平衡进行加权训练来校正。然而，测试类平衡在实践中往往是未知的。在本文中，我们考虑了一个半监督学习设置，标记的训练样本和未标记的测试样本是可用的，并提出了一个类平衡估计的基础上的能量距离。通过实验，我们证明了所提出的方法是计算效率比现有的方法，具有可比的精度。
In many real-world classication problems, the class balance often changes between training and test datasets, due to sample selection bias or the non-stationarity of the environment. Naive classier training under such changes of class balance systematically yields a biased solution. It is known that such a systematic bias can be corrected by weighted training according to the test class balance. However, the test class balance is often unknown in practice. In this paper, we consider a semi- supervised learning setup where labeled training samples and unlabeled test samples are available and propose a class balance estimator based on the energy distance. Through experiments, we demonstrate that the proposed method is computationally much more efficient than existing approaches, with comparable accuracy.