A Construction of Robust Representations for Small Data Sets Using Broad Learning System
A Construction of Robust Representations for Small Data Sets Using Broad Learning System
复制标题
使用广泛的学习系统构建小数据集的鲁棒表示
DOI：
10.1109/tsmc.2019.2957818
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Yong Shi
中科院分区：
文献类型：
--
作者：
Huimin Tang;Peiwu Dong;Yong Shi
特征处理是建模的重要步骤，可以提高机器学习模型的准确性。特征提取方法可以有效地从高维数据集中提取特征，提高任务的准确性。然而，特征提取方法的性能是不稳定的低维数据集。本文将广义学习系统（BLS）扩展为一个框架，用于在低维和小数据集中构建鲁棒的表示。首先，BLS从监督预测方法转变为集成特征提取方法。其次，特征提取方法，而不是随机映射被用来生成映射的功能。第三，深度表示，称为增强功能，从集成映射的功能。第四，可以随机选择用于生成映射特征和增强特征的数据。映射特征和增强特征的集合可以提供鲁棒的表示以增强下游任务的性能。最后以一个基于标签的自动编码器（LA）嵌入BLS框架为例，验证了该框架的有效性。提出了一种随机LA（RLA）算法，以生成更多的不同特征。实验结果表明，BLS框架可以构造鲁棒的表示，并显着提高机器学习模型的性能。
Feature processing is an important step for modeling and can improve the accuracy of machine learning models. Feature extraction methods can effectively extract features from high-dimensional data sets and enhance the accuracy of tasks. However, the performance of feature extraction methods is not stable in low-dimensional data sets. This article extends the broad learning system (BLS) to a framework for constructing robust representations in low-dimensional and small data sets. First, the BLS changed from a supervised prediction method to an ensemble feature extraction method. Second, feature extraction methods instead of random mapping are used to generate mapped features. Third, deep representations, called enhancement features, are learned from the ensemble mapped features. Fourth, data for generating mapped features and enhancement features can be randomly selected. The ensemble of mapped features and enhancement features can provide robust representations to enhance the performance of downstream tasks. A label-based autoencoder (LA) is embedded in the BLS framework as an example to show the effectiveness of the framework. A random LA (RLA) is presented to generate more different features. The experimental results show that the BLS framework can construct robust representations and significantly promote the performance of machine learning models.