The generative adversarial network (GAN) is a good example of a strong-performing, neural network-based generative model, even though it does have some drawbacks of its own. Mode collapsing and the difficulty in finding the optimal network structure are two of the most concerning issues. In this paper, we address these two issues at the same time by proposing a neuro-evolutionary approach with an agile evaluation method for the fast evolution of robust deep architectures that avoid mode collapsing. The computation of Pareto set approximations with GANs is chosen as a suitable benchmark to evaluate the quality of our approach. Furthermore, we demonstrate the consistency, scalability, and generalization capabilities of the proposed method, which shows its potential applications to many areas. We finally readdress the issue of designing this kind of models by analyzing the characteristics of the best performing GAN specifications, and conclude with a set of general guidelines. This results in a reduction of the many-dimensional problem of structural manual design or automated search.

生成对抗网络（GAN）是基于神经网络的强大性能生成模型的一个很好的例子，尽管它确实有其自身的一些缺点。模式崩溃和寻找最佳网络结构的困难是最令人关注的两个问题。在本文中，我们通过提出一种神经进化方法和一种敏捷评估方法来同时解决这两个问题，从而快速发展了稳健的深度架构，避免了模式崩溃。选择使用GAN计算帕累托集近似值作为评估我们方法质量的合适基准。此外，我们演示了所提出方法的一致性，可伸缩性和泛化能力，从而显示了其在许多领域的潜在应用。我们最后将通过分析性能最佳的GAN规范的特征来解决设计此类模型的问题，并以一套通用准则作为总结。这减少了结构手动设计或自动搜索的多维问题。