arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.04170cs.LG
收藏

不平衡问题的少数类和多数类综合过采样方法

A Synthetic Over-sampling method with Minority and Majority classes for imbalance problems

University of Melbourne(墨尔本大学)

Hadi A. Khorshidi, Uwe Aickelin

摘要:

类别不平衡是对许多现实世界案例进行分类的一个重大挑战。合成过采样方法已经有效地提高了分类器的性能不平衡的问题。然而,大多数合成过采样方法产生的凸包内的现有少数实例形成的非多样化的合成实例,因为他们只集中在少数类,而忽略了大量的信息提供的多数类。它们通常也不能很好地处理极不平衡的数据,因为少数实例越少,生成合成实例的信息就越少。此外,现有的方法,生成合成实例使用多数类分布信息不能有效地执行时,多数类具有多模态分布。我们提出了一种新的方法来生成多样性和适应性的合成实例,使用合成过采样与少数和多数类(SOMM)。SOMM在少数数据空间内生成合成实例。它更新生成的实例自适应包括两个类的邻域。因此,SOMM表现良好的二进制和多类不平衡问题。我们研究的性能SOMM的二进制和多类问题使用基准数据集不同的不平衡水平。实验结果表明,SOMM的优越性相比,其他现有的方法。

英文摘要:

Class imbalance is a substantial challenge in classifying many real-world cases. Synthetic over-sampling methods have been effective to improve the performance of classifiers for imbalance problems. However, most synthetic over-sampling methods generate non-diverse synthetic instances within the convex hull formed by the existing minority instances as they only concentrate on the minority class and ignore the vast information provided by the majority class. They also often do not perform well for extremely imbalanced data as the fewer the minority instances, the less information to generate synthetic instances. Moreover, existing methods that generate synthetic instances using the majority class distributional information cannot perform effectively when the majority class has a multi-modal distribution. We propose a new method to generate diverse and adaptable synthetic instances using Synthetic Over-sampling with Minority and Majority classes (SOMM). SOMM generates synthetic instances diversely within the minority data space. It updates the generated instances adaptively to the neighbourhood including both classes. Thus, SOMM performs well for both binary and multiclass imbalance problems. We examine the performance of SOMM for binary and multiclass problems using benchmark data sets for different imbalance levels. The empirical results show the superiority of SOMM compared to other existing methods.

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。

↑