About this document

Federated Learning for GANs: CAP Framework by nguyenduckienuet is a document available to read on EtoBox.

This paper presents a novel federated learning framework called Collaborated gAme Parallel Learning (CAP) for training Generative Adversarial Networks (GANs) at the edge, addressing challenges like bandwidth, privacy, and Non-IID data issues. The proposed CAP-GAN incorporates a Mix-Generator module to enhance performance on personalized datasets and allows for collaborative learning among cloud, edge servers, and devices. Experimental results demonstrate that CAP-GAN outperforms existing state-of-the-art al

Author

nguyenduckienuet

Language

EN