arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.04655cs.LGcs.AI
收藏

具有理论保证的联邦GANs训练:一种通用聚合方法

Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach

Rutgers University(罗格斯大学);Stony Brook University(石溪大学)

Yikai Zhang, Hui Qu, Qi Chang, Huidong Liu, Dimitris Metaxas, Chao Chen

摘要:

最近,生成对抗网络(GANs)已经证明了它们在联邦学习中的潜力,即,从多个站点私有托管的数据中学习集中式模型。联合GAN联合训练集中式生成器和托管在不同站点的多个私有鉴别器。联邦GAN的一个主要理论挑战是本地数据分布的异质性。传统的方法不能保证学习目标分布,这是一个高度不同的本地分布的混合。本文解决了这一理论挑战,并首次为联邦GAN提供了一个可证明的正确框架。我们提出了一种新的方法,称为通用聚合,它模拟了一个集中式的鉴别器通过仔细聚合的所有私人的混合物。我们证明了用这种模拟的集中式神经网络训练的生成器可以学习所需的目标分布。通过合成和真实数据集,我们表明,我们的方法可以学习现有联邦GAN方法失败的大部分不同分布的混合。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑