Sorry, you need to enable JavaScript to visit this website.

LEARNING GEOGRAPHICALLY DISTRIBUTED DATA FOR MULTIPLE TASKS USING GENERATIVE ADVERSARIAL NETWORKS

Citation Author(s):
Yaqi Wang, Mehdi Nikkhah, Xiaoqing Zhu, Wai-tian Tan, and Rob Liston
Submitted by:
Xiaoqing Zhu
Last updated:
16 September 2019 - 11:19am
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Yaqi Wang, Xiaoqing Zhu, and Wai-tian Tan
Paper Code:
2489

Abstract

We present a novel method that supports the learning of multiple classification tasks from geographically distributed data. By combining locally trained generative adversarial networks (GANs) with a small fraction of original data samples, our proposed scheme can train multiple discriminative models at a central location with low communication overhead. Experiments using common image datasets (MNIST, CIFAR-10, LSUN-20, Celeb-A) show that our proposed scheme can achieve comparable classification accuracy as the ideal classifier trained using all data from all sites. We further demonstrate that our method can scale to 10 sites without sacrificing classification accuracy for large datasets such as LSUN-20.

up
0 users have voted: