Deep Similarity Learning Loss Functions in Data Transformation for Class Imbalance
This work addresses classification challenges in multi-class imbalanced datasets, offering a novel pre-processing approach that modifies feature distributions without altering class sizes, though it is incremental in nature.
The paper tackles multi-class imbalanced data classification by using deep neural networks to learn new embedded representations through triplet loss functions, achieving improved performance over existing pre-processing methods and basic neural networks on benchmark datasets.
Improving the classification of multi-class imbalanced data is more difficult than its two-class counterpart. In this paper, we use deep neural networks to train new representations of tabular multi-class data. Unlike the typically developed re-sampling pre-processing methods, our proposal modifies the distribution of features, i.e. the positions of examples in the learned embedded representation, and it does not modify the class sizes. To learn such embedded representations we introduced various definitions of triplet loss functions: the simplest one uses weights related to the degree of class imbalance, while the next proposals are intended for more complex distributions of examples and aim to generate a safe neighborhood of minority examples. Similarly to the resampling approaches, after applying such preprocessing, different classifiers can be trained on new representations. Experiments with popular multi-class imbalanced benchmark data sets and three classifiers showed the advantage of the proposed approach over popular pre-processing methods as well as basic versions of neural networks with classical loss function formulations.