CS Events

Qualifying Exam

Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data


Download as iCal file

Thursday, May 28, 2020, 02:00pm - 03:30pm


Speaker: Qi Chang

Location : Remote via Webex


Prof. Dimitri Metaxas; Prof. Konstantinos Michmizos; Prof. Sungjin Ahn; Prof. Aaron Bernstein

Event Type: Qualifying Exam

Abstract: We propose a data privacy-preserving and communication efficient distributed GAN learning framework named Distributed Asynchronized Discriminator GAN (AsynDGAN). Our proposed framework aims to train a central generator learns from distributed discriminator, and use the generated synthetic image solely to train the segmentation model. We validate the proposed framework on the application of health entities learning problem which is known to be privacy sensitive. Our experiments show that our approach: 1) could learn the real image’s distribution from multiple datasets without sharing the patient’s raw data. 2) is more efficient and requires lower bandwidth than other distributed deep learning methods. 3) achieves higher performance compared to the model trained by one real dataset, and almost the same performance compared to the model trained by all real datasets. 4) has provable guarantees that the generator could learn the distributed distribution in an all important fashion thus is unbiased.


Meeting number: 792 132 464
Password: Y8PaQcik5f4


Join by video system
Dial This email address is being protected from spambots. You need JavaScript enabled to view it.
You can also dial and enter your meeting number.

Join by phone
+1-650-429-3300 USA Toll
Access code: 792 132 464