RAC-GAN: Iterative Dual-Objective Over and Under Sampling for Imbalanced Datasets

This paper introduces a novel framework named the Ranking Auxiliary Classifier Generative Adversarial Network (RAC-GAN), which leverages a dual strategy involving a Generative Adversarial Network (GAN)-based data generator for oversampling and a Reinforcement Learning (RL)-based ranker for undersampling. The RAC-GAN is designed to concurrently oversample and undersample both majority and minority classes during each training epoch, aiming to enhance model performance on imbalanced datasets. The proposed framework is fully end-to-end trainable. At each training iteration, it learns: (i) when to perform oversampling, undersampling, or both operations; (ii) how to identify relevant regions in the data for these operations; and (iii) the extent to which these operations should be carried out. We present experimental results on 11 real-world imbalanced datasets, varying in size and complexity, and evaluated against a range of heuristic and state-of-the-art baselines. The outcomes demonstrate the efficacy of the RAC-GAN framework in improving model performance across different classifiers.