Generative Adversarial Networks (GANs) are popular tools for generative modeling. The dynamics of their adversarial learning give rise to convergence pathologies during training such as mode and discriminator collapse. In machine learning, ensembles of predictors demonstrate better results than a single predictor for many tasks. In this study, we apply two evolutionary algorithms (EAs) to create ensembles to re-purpose generative models, i.e., given a set of heterogeneous generators that were optimized for one objective (e.g., minimize Frechet Inception Distance), create ensembles of them for optimizing a different objective (e.g., maximize the diversity of the generated samples). The first method is restricted by the exact size of the ensemble and the second method only restricts the upper bound of the ensemble size. Experimental analysis on the MNIST image benchmark demonstrates that both EA ensembles creation methods can re-purpose the models, without reducing their original functionality. The EA-based demonstrate significantly better performance compared to other heuristic-based methods. When comparing both evolutionary, the one with only an upper size bound on the ensemble size is the best.

中文翻译：

---

用进化计算重新利用异构生成集成

生成对抗网络 (GAN) 是用于生成建模的流行工具。他们的对抗性学习的动态会在训练过程中引起收敛病态，例如模式和判别器崩溃。在机器学习中，对于许多任务，预测器的集成比单个预测器表现出更好的结果。在这项研究中，我们应用两种进化算法 (EA) 来创建集成以重新利用生成模型，即，给定一组针对一个目标优化的异构生成器（例如，最小化 Frechet Inception 距离），创建它们的集成以用于优化不同的目标（例如，最大化生成样本的多样性）。第一种方法受集成的确切大小限制，而第二种方法仅限制集成大小的上限。MNIST 图像基准的实验分析表明，两种 EA 集成创建方法都可以重新利用模型，而不会减少其原始功能。与其他基于启发式的方法相比，基于 EA 的方法表现出明显更好的性能。比较两者的进化时，只有集合大小有上限的那个是最好的。