Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Still, their high computational demands prohibit their deployment in practical scenarios like edge devices. Existing GAN compression methods mainly rely on knowledge distillation or convolutional classifiers' pruning techniques. Thus, they neglect the critical characteristic of GANs: their local density structure over their learned manifold. Accordingly, we approach GAN compression from a new perspective by explicitly encouraging the pruned model to preserve the density structure of the original parameter-heavy model on its learned manifold. We facilitate this objective for the pruned model by partitioning the learned manifold of the original generator into local neighborhoods around its generated samples. Then, we propose a novel pruning objective to regularize the pruned model to preserve the local density structure over each neighborhood, resembling the kernel density estimation method. Also, we develop a collaborative pruning scheme in which the discriminator and generator are pruned by two pruning agents. We design the agents to capture interactions between the generator and discriminator by exchanging their peer's feedback when determining corresponding models' architectures. Thanks to such a design, our pruning method can efficiently find performant sub-networks and can maintain the balance between the generator and discriminator more effectively compared to baselines during pruning, thereby showing more stable pruning dynamics. Our experiments on image translation GAN models, Pix2Pix and CycleGAN, with various benchmark datasets and architectures demonstrate our method's effectiveness.

翻译：生成对抗网络在建模复杂数据分布以实现图像到图像翻译方面取得了显著成功，但其高计算需求阻碍了在边缘设备等实际场景中的部署。现有GAN压缩方法主要依赖知识蒸馏或卷积分类器剪枝技术，因而忽略了GAN的关键特征：其学习流形上的局部密度结构。为此，我们从新视角提出GAN压缩方法，通过显式鼓励剪枝模型保留原始参数密集型模型在其学习流形上的密度结构。为实现该目标，我们将原始生成器的学习流形划分为生成样本周围的局部邻域，进而提出一种新颖的剪枝目标，通过正则化剪枝模型保留每个邻域上的局部密度结构（类似于核密度估计方法）。此外，我们开发了协作剪枝方案，由两个剪枝代理分别对判别器和生成器进行剪枝。我们设计代理通过交换彼此反馈（在确定对应模型架构时）来捕获生成器与判别器之间的交互。得益于该设计，我们的剪枝方法能高效发现性能优越的子网络，并在剪枝过程中比基线方法更有效地维持生成器与判别器之间的平衡，从而展现更稳定的剪枝动态。我们在图像翻译GAN模型Pix2Pix和CycleGAN上，结合多种基准数据集和架构的实验证明了该方法的有效性。