Imbalanced Classification via Explicit Gradient Learning From Augmented Data
This addresses the challenge of imbalanced data in real-world classification tasks, where neural networks often underperform on minority classes, offering a novel solution that could improve accuracy in domains like fraud detection or medical diagnosis.
The paper tackles imbalanced classification by proposing a deep meta-learning technique that augments datasets with new minority instances, which are explicitly learned during training. The method is demonstrated to outperform existing approaches on synthetic and real-world datasets with various imbalance ratios.
Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing approaches attempt to eliminate the bias through data re-sampling or re-weighting the loss in the learning process. Still, these methods tend to overfit the minority samples and perform poorly when the structure of the minority class is highly irregular. Here, we propose a novel deep meta-learning technique to augment a given imbalanced dataset with new minority instances. These additional data are incorporated in the classifier's deep-learning process, and their contributions are learned explicitly. The advantage of the proposed method is demonstrated on synthetic and real-world datasets with various imbalance ratios.