Federated Generative Adversarial Learning release_mavjckwfy5bl5erorxnryfbqhe

by Chenyou Fan, Ping Liu

Released as a article .

2020  

Abstract

This work studies training generative adversarial networks under the federated learning setting. Generative adversarial networks (GANs) have achieved advancement in various real-world applications, such as image editing, style transfer, scene generations, etc. However, like other deep learning models, GANs are also suffering from data limitation problems in real cases. To boost the performance of GANs in target tasks, collecting images as many as possible from different sources becomes not only important but also essential. For example, to build a robust and accurate bio-metric verification system, huge amounts of images might be collected from surveillance cameras, and/or uploaded from cellphones by users accepting agreements. In an ideal case, utilize all those data uploaded from public and private devices for model training is straightforward. Unfortunately, in the real scenarios, this is hard due to a few reasons. At first, some data face the serious concern of leakage, and therefore it is prohibitive to upload them to a third-party server for model training; at second, the images collected by different kinds of devices, probably have distinctive biases due to various factors, e.g., collector preferences, geo-location differences, which is also known as "domain shift". To handle those problems, we propose a novel generative learning scheme utilizing a federated learning framework. Following the configuration of federated learning, we conduct model training and aggregation on one center and a group of clients. Specifically, our method learns the distributed generative models in clients, while the models trained in each client are fused into one unified and versatile model in the center. We perform extensive experiments to compare different federation strategies, and empirically examine the effectiveness of federation under different levels of parallelism and data skewness.
In text/plain format

Archived Files and Locations

application/pdf  1.1 MB
file_gxheqemm5vesvncschngan3tg4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-05-07
Version   v1
Language   en ?
arXiv  2005.03793v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2a93b7a5-2e2e-44b3-9930-3fe20473d74b
API URL: JSON