FedGAN: Federated Generative Adversarial Networks for Distributed Data
This addresses the challenge of training GANs in federated settings for applications like image and time series data, but it is incremental as it adapts existing methods to distributed constraints.
The paper tackles the problem of training generative adversarial networks (GANs) on distributed, non-IID data with communication and privacy constraints by proposing FedGAN, which uses local generators and discriminators synced via parameter averaging. The result shows FedGAN converges similarly to distributed GANs while reducing communication complexity and demonstrating robustness to reduced communications.
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.