Exploring the Evolution of GANs through Quality Diversity

TL;DR

This paper introduces a quality-diversity evolutionary algorithm for GANs that enhances diversity and performance, addressing training challenges and improving upon previous methods like COEGAN.

Contribution

The paper applies a Novelty Search with Local Competition algorithm to evolve GANs, improving diversity and model quality over existing evolutionary approaches.

Findings

Increased diversity of GAN solutions.

Enhanced performance of evolved GAN models.

Global competition approach finds better models.

Abstract

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model should be previously designed by hand to ensure training success. In this context, evolutionary algorithms such as COEGAN were proposed to solve the challenges in GAN training. Nevertheless, the lack of diversity and premature optimization can be found in some of these solutions. We propose in this paper the application of a quality-diversity algorithm in the evolution of GANs. The solution is based on the Novelty Search with Local Competition (NSLC) algorithm, adapting the concepts used in COEGAN to this new proposal. We compare our proposal with the original COEGAN model and with an alternative version using a global competition approach. The experimental results evidenced that our proposal increases the diversity of the discovered solutions and leverage the performance of the models found by the algorithm. Furthermore, the global competition approach was able to consistently find better models for GANs.