RDPVR: Random Data Partitioning with Voting Rule for Machine Learning from Class-Imbalanced Datasets

Since most classifiers are biased toward the dominant class, class imbalance is a challenging problem in machine learning. The most popular approaches to solving this problem include oversampling minority examples and undersampling majority examples. Oversampling may increase the probability of overfitting, whereas undersampling eliminates examples that may be crucial to the learning process. We present a linear time resampling method based on random data partitioning and a majority voting rule to address both concerns, where an imbalanced dataset is partitioned into a number of small subdatasets, each of which must be class balanced. After that, a specific classifier is trained for each subdataset, and the final classification result is established by applying the majority voting rule to the results of all of the trained models. We compared the performance of the proposed method to some of the most well-known oversampling and undersampling methods, employing a range of classifiers, on 33 benchmark machine learning class-imbalanced datasets. The classification results produced by the classifiers employed on the generated data by the proposed method were comparable to most of the resampling methods tested, with the exception of SMOTEFUNA, which is an oversampling method that increases the probability of overfitting. The proposed method produced results that were comparable to the Easy Ensemble (EE) undersampling method. As a result, for solving the challenge of machine learning from class-imbalanced datasets, we advocate using either EE or our method.

MULTILABEL OVER-SAMPLING AND UNDER-SAMPLING WITH CLASS ALIGNMENT FOR IMBALANCED MULTILABEL TEXT CLASSIFICATION

Simultaneous multiple labelling of documents, also known as multilabel text classification, will not perform optimally if the class is highly imbalanced. Class imbalanced entails skewness in the fundamental data for distribution that leads to more difficulty in classification. Random over-sampling and under-sampling are common approaches to solve the class imbalanced problem. However, these approaches have several drawbacks; the under-sampling is likely to dispose of useful data, whereas the over-sampling can heighten the probability of overfitting. Therefore, a new method that can avoid discarding useful data and overfitting problems is needed. This study proposes a method to tackle the class imbalanced problem by combining multilabel over-sampling and under-sampling with class alignment (ML-OUSCA). In the proposed ML-OUSCA, instead of using all the training instances, it draws a new training set by over-sampling small size classes and under-sampling big size classes. To evaluate our proposed ML-OUSCA, evaluation metrics of average precision, average recall and average F-measure on three benchmark datasets, namely, Reuters-21578, Bibtex, and Enron datasets, were performed. Experimental results showed that the proposed ML-OUSCA outperformed the chosen baseline random resampling approaches; K-means SMOTE and KNN-US. Thus, based on the results, we can conclude that designing a resampling method based on the class imbalanced together with class alignment will improve multilabel classification even better than just the random resampling method.