Chargement Évènements
Chercher

Event Views Navigation

Chargement Évènements

« Tous les évènements

  • Cet évènement est passé

Talk by Lydia Chen on Decentralized Data Synthesizer

18 novembre 2021 à 14 h 30 min - 15 h 30 min

We are pleased to host Dr. Lydia Chen from the Delft University of Technology, The Netherlands (TU Delft).

She will give a talk entitled ‘Decentralized Data Synthesizer‘ on November, 18 in Lyon.

When: November, 18 at 14h30 – 15h30
Where: Campus de la Doua, bâtiment Nautibus, rez-de-chaussée, salle visioconférence. 23-25 avenue Pierre de Coubertin, 69100 Villeurbanne

Abstract
While data sharing is crucial for knowledge development, privacy concerns and strict regulation, e.g., GDPR, unfortunately limit its full effectiveness. Synthetic data generated by generative adversarial networks (GANs) emerges as an alternative to enable data sharing across organization boundaries, e.g., hospitals and banks. However, the state of practise of centralized data collection and model training undermines the data privacy. In this talk, I will first present novel generative adversarial networks (GANs) for synthesizing tabular data. I will then introduce a federated learning framework that enables training tabular GANs on decentralized data sources without directly accessing them – privacy by design. I will discuss choices of decentralized architecture for tabular GANs, and how to further enhance its privacy by combining differential privacy.

Bio:

Lydia Y. Chen is an Associate Professor in the Department of Computer Science at the Delft University of Technology in The Netherlands. Prior to joining TU Delft, she was a research staff member at the IBM Research Zurich Lab from 2007 to 2018. She holds a PhD from Pennsylvania State University and a BA from National Taiwan University. Her research interests are distributed machine learning, dependability management, resource allocation for large-scale data processing systems and services. More specifically, her work focuses on developing stochastic and machine learning models, and applying these techniques to application domains, such as data centers and AI systems.

She has published more than 100 papers in peer-reviewed journals, including IEEE Transactions on Distributed Systems and IEEE Transactions on Service Computing, and in conference proceedings, including INFOCOM, SIGMETRICS, DSN, and EUROSYS. She was a co-recipient of the best paper awards at CCGrid’15 and eEnergy’15. She received TU Delft technology fellowship in 2018. She was program co-chair for IEEE ICAC 2019, Middleware Industry track 2018, track vice-chair for ICDCS 2018, and DIAS 2017. She has served on the editorial boards of IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Parallel and Distributed Systems, IEEE Transactions on Service Computing and IEEE Transactions on Network and Service Management. She is a Senior Member of IEEE.

Détails

Date :
18 novembre 2021
Heure :
14 h 30 min - 15 h 30 min

Lieu

Bâtiment Nautibus, salle visioconf (RdC)
23-25 avenue Pierre de Coubertin
Villeurbanne, 69100 France
+ Google Map