A Label Noise Robust Stacked Auto-Encoder Algorithm for Inaccurate Supervised Classification Problems
A Label Noise Robust Stacked Auto-Encoder Algorithm for Inaccurate Supervised Classification Problems
复制标题
针对不准确监督分类问题的标签噪声鲁棒堆叠自动编码器算法
DOI：
10.1155/2019/2182616
复制
发表时间：
2019
影响因子：
--
通讯作者：
Liang Jun
中科院分区：
文献类型：
--
作者：
Wang Zi yang;Luo Xiao yi;Liang Jun
在实际应用中，标签噪声和特征噪声是两个主要的噪声源。与特征噪声类似，标签噪声对训练分类模型有很大的不利影响。基于深度学习方法在正常分类问题中的成功应用，本文提出了一种新的框架LNC-SDAE来处理被标签噪声污染的数据集，即所谓的不准确监督问题。LNC-SDAE框架包含初步的标签噪声净化部分和堆叠式去噪自动编码器。在初步的标签噪声净化部分，采用K-折交叉验证的思想对误标样本进行检测和重新标记。经过标签噪声清洗部分的预处理后，清洗后的训练数据集被输入到堆叠去噪自动编码器中，以学习用于分类的稳健表示。被破坏的UCI标准数据集和被破坏的真实工业数据集被用于测试，两者都包含一定比例的标签噪声(该比率从0%变化到30%)。实验结果证明了LNC-SDAE的有效性，其学习的表示具有较强的鲁棒性。
In real applications, label noise and feature noise are two main noise sources. Similar to feature noise, label noise imposes great detriment on training classification models. Motivated by successful application of deep learning method in normal classification problems, this paper proposes a new framework called LNC-SDAE to handle those datasets corrupted with label noise, or so-called inaccurate supervision problems. The LNC-SDAE framework contains a preliminary label noise cleansing part and a stacked denoising auto-encoder. In preliminary label noise cleansing part, the K-fold cross-validation thought is applied for detecting and relabeling those mislabeled samples. After being preprocessed by label noise cleansing part, the cleansed training dataset is then input into the stacked denoising auto-encoder to learn robust representation for classification. A corrupted UCI standard dataset and a corrupted real industrial dataset are used for test, both of which contain a certain proportion of label noise (the ratio changes from 0% to 30%). The experiment results prove the effectiveness of LNC-SDAE, the representation learnt by which is shown robust.