We propose Federated Generative Adversarial Network (FedGAN) for training a GAN across distributed sources of non-independent-and-identically-distributed data sources subject to communication and privacy constraints. Our algorithm uses local generators and discriminators which are periodically synced via an intermediary that averages and broadcasts the generator and discriminator parameters. We theoretically prove the convergence of FedGAN with both equal and two time-scale updates of generator and discriminator, under standard assumptions, using stochastic approximations and communication efficient stochastic gradient descents. We experiment FedGAN on toy examples (2D system, mixed Gaussian, and Swiss role), image datasets (MNIST, CIFAR-10, and CelebA), and time series datasets (household electricity consumption and electric vehicle charging sessions). We show FedGAN converges and has similar performance to general distributed GAN, while reduces communication complexity. We also show its robustness to reduced communications.

中文翻译：

---

FedGAN：分布式数据的联合生成对抗网络

我们提出了联合生成对抗网络 (FedGAN)，用于在受通信和隐私约束的非独立和相同分布式数据源的分布式源中训练 GAN。我们的算法使用本地生成器和鉴别器，这些生成器和鉴别器通过中介器定期同步，该中间器对生成器和鉴别器参数进行平均和广播。我们在标准假设下，使用随机近似和通信高效的随机梯度下降，在理论上证明了 FedGAN 与生成器和鉴别器的相等和两个时间尺度更新的收敛性。我们在玩具示例（2D 系统、混合高斯和瑞士角色）、图像数据集（MNIST、CIFAR-10 和 CelebA）上试验 FedGAN，和时间序列数据集（家庭用电量和电动汽车充电会话）。我们展示了 FedGAN 收敛并具有与一般分布式 GAN 相似的性能，同时降低了通信复杂性。我们还展示了它对减少通信的鲁棒性。