Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification
This work addresses a long-standing problem in machine learning and deep learning, providing a solution for handling imbalanced classification, which is significant for researchers and practitioners dealing with real-world datasets.
The authors tackled the problem of class imbalance in machine learning and deep learning models, proposing a framework that generates synthetic data instances, resulting in superior performance over state-of-the-art algorithms. The framework achieved this through a data-driven approach to oversampling, enhancing the model's representation power.
Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue, traditional sampling techniques are often decoupled from the training phase of the predictive model, resulting in suboptimal representations. To address this, we propose a novel learning framework that can generate synthetic data instances in a data-driven manner. The proposed framework formulates the oversampling process as a composition of discrete decision criteria, thereby enhancing the representation power of the model's learning process. Extensive experiments on the imbalanced classification task demonstrate the superiority of our framework over state-of-the-art algorithms.