arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.03793cs.LGcs.CV
收藏

联邦生成对抗学习

Federated Generative Adversarial Learning

Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)(深圳人工智能与机器人学会);Institute of High Performance Computing (IHPC), A*STAR(高性能计算研究所 (IHPC),A*STAR)

Chenyou Fan, Ping Liu

摘要:

本文研究了在联邦学习环境下训练生成对抗网络的问题。生成对抗网络(GANs)在各种现实世界的应用中取得了进步,例如图像编辑,风格转移,场景生成等。然而,与其他深度学习模型一样,GANs在实际情况下也会遇到数据限制问题。为了提高GANs在目标任务中的性能,从不同来源收集尽可能多的图像不仅重要,而且至关重要。例如,为了构建鲁棒且准确的生物计量验证系统,可以从监控摄像机收集大量图像,和/或由接受协议的用户从手机上传。在理想情况下,利用从公共和私人设备上传的所有数据进行模型训练是简单的。不幸的是,在真实场景中,由于一些原因,这是很难的。首先,一些数据面临严重的泄漏问题,因此禁止将它们上传到第三方服务器进行模型训练;其次,不同类型的设备收集的图像可能由于各种因素而具有不同的偏差,$\textit{e.g.}$,收集者偏好,地理位置差异,这也被称为“域偏移”。为了解决这些问题,我们提出了一种新的生成式学习方案,利用联邦学习框架。按照联邦学习的配置,我们在一个中心和一组客户端上进行模型训练和聚合。具体来说,我们的方法在客户端学习分布式生成模型,而在每个客户端训练的模型在中心融合成一个统一的通用模型。我们进行了大量的实验,比较不同的联邦战略,并实证研究联邦的有效性,在不同程度的并行性和数据偏斜。

英文摘要:

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, $\textit{e.g.}$, 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.

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。

↑