Towards Mitigating Mode Collapse: An Entropy-Based Approach to Enhance WGAN

Generative Adversarial Networks (GANs) are powerful tools for generating synthetic data, making them highly valuable in data-driven research by addressing data scarcity/imbalance in real-world datasets. However, GANs often suffer from mode collapse, where the generator produces a limited range of outputs, failing to capture the full diversity of the target distribution. While the Wasserstein GAN (WGAN) improves training stability and mitigates mode collapse compared to traditional GANs, it is not entirely immune to this issue. In this paper, we propose an Entropy-Augmented WGAN (E-WGAN), which incorporates an additional entropy-based information into the generator's loss function to explicitly promote diversity in generated samples. By maximizing the entropy of the generator's output distribution, we aim to enhance the diversity of WGAN-generated data without compromising quality. Our results show that E-WGAN effectively increases the diversity of generated samples while preserving the stability and high quality of the outputs seen in standard WGANs. The proposed method offers promising results to further mitigating mode collapse and enhancing the generative capabilities of WGANs.