Combine vector quantization and support vector machine for imbalanced datasets

摘要

In cases of extremely imbalanced dataset with high dimensions, standard machine learning techniques tend to be overwhelmed by the large classes. This paper rebalances skewed datasets by compressing the majority class. This approach combines Vector Quantization and Support Vector Machine and constructs a new approach, VQ-SVM, to rebalance datasets without significant information loss. Some issues, e.g. distortion and support vectors, have been discussed to address the trade-off between the information loss and undersampling. Experiments compare VQ-SVM and standard SVM on some imbalanced datasets with varied imbalance ratios, and results show that the performance of VQ-SVM is superior to SVM, especially in case of extremely imbalanced large datasets.