Exploring the Evolution of GANs through Quality Diversity

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.

Published in GECCO 2020

References in corpus (12)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Illuminating search spaces by mapping elites
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• Spatial Evolutionary Generative Adversarial Networks
• COEGAN: Evaluating the Coevolution Effect in Generative Adversarial Networks
• Towards Distributed Coevolutionary GANs
• Evolutionary Generative Adversarial Networks

Cited by in corpus (3)

• Meta Learning Black-Box Population-Based Optimizers
• Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation
• EvoGAN: An Evolutionary Computation Assisted GAN