Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach
Recently, Generative Adversarial Networks (GANs) have demonstrated their potential in federated learning, i.e., learning a centralized model from data privately hosted by multiple sites. A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites. A major theoretical challenge for the federated GAN is the heterogeneity of the local data distributions. Traditional approaches cannot guarantee to learn the target distribution, which isa mixture of the highly different local distributions. This paper tackles this theoretical challenge, and for the first time, provides a provably correct framework for federated GAN. We propose a new approach called Universal Aggregation, which simulates a centralized discriminator via carefully aggregating the mixture of all private discriminators. We prove that a generator trained with this simulated centralized discriminator can learn the desired target distribution. Through synthetic and real datasets, we show that our method can learn the mixture of largely different distributions where existing federated GAN methods fail.
Code (1)
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks
Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning. Despite its remarkable empirical performance, there are limited theoretical studies on the statistical properties of GANs. Th…
Fed-TGAN: Federated Learning Framework for Synthesizing Tabular Data
Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. Recently, federated learning (FL) is…
Federated LearningPrivacy PreservingUniversally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remai…
Federated LearningStabilizing GANs' Training with Brownian Motion Controller
The training process of generative adversarial networks (GANs) is unstable and does not converge globally. In this paper, we examine the stability of GANs from the perspective of control theory and propose a universal hi…
Towards GANs' Approximation Ability
Generative adversarial networks (GANs) have attracted intense interest in the field of generative models. However, few investigations focusing either on the theoretical analysis or on algorithm design for the approximati…