A
Adrien Pavao
Researcher at Université Paris-Saclay
Publications - 14
Citations - 156
Adrien Pavao is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 6, co-authored 12 publications receiving 80 citations. Previous affiliations of Adrien Pavao include University of Paris-Sud & French Institute for Research in Computer Science and Automation.
Papers
More filters
Journal ArticleDOI
Generation and evaluation of privacy preserving synthetic health data
TL;DR: An end-to-end workflow based on the generative adversarial network (GAN) method, HealthGAN, that creates privacy preserving synthetic health data that is compared against five other baseline methods and provides the best privacy and footprint.
Journal ArticleDOI
Privacy Preserving Synthetic Health Data
TL;DR: This work examines the feasibility of using synthetic medical data generated by GANs in the classroom, to teach data science in health infor-matics and presents an end-to-end methodology to retain instructional utility, while preserving privacy to a level, which meets regulatory requirements.
Proceedings ArticleDOI
Assessing privacy and quality of synthetic health data
TL;DR: This paper provides additional novel metrics to quantify the susceptibility of these generative models to membership inference attacks and introduces Discriminator Testing, a new method of determining whether the different generators overfit on the training data, potentially resulting in privacy losses.
Proceedings Article
Privacy Preserving Synthetic Health Data.
TL;DR: In this article, the feasibility of using synthetic medical data generated by GANs in the classroom, to teach data science in health infor-matics is examined, and an end-to-end methodology to retain instructional utility, while preserving privacy to a level, which meets regulatory requirements is presented.
Journal ArticleDOI
Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019
Zhengying Liu,Adrien Pavao,Zhen Xu,Sergio Escalera,Fabio Ferreira,Isabelle Guyon,Sirui Hong,Frank Hutter,Rongrong Ji,Julio C. S. Jacques Junior,Ge Li,Marius Lindauer,Luo Zhipeng,Meysam Madadi,Thomas Nierhoff,Kangning Niu,Chunguang Pan,Danny Stoll,Sebastien Treguer,Jin Wang,Peng Wang,Chenglin Wu,Youcheng Xiong,Arber Zela,Yang Zhang +24 more
TL;DR: This paper reports the results and post-challenge analyses of ChaLearn’s AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair comparisons.