Youlong Ding
YOU?
Author Swipe
View article: Delving into Differentially Private Transformer
Delving into Differentially Private Transformer Open
Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency. This paper delves into the probl…
View article: PAC Privacy Preserving Diffusion Models
PAC Privacy Preserving Diffusion Models Open
Data privacy protection is garnering increased attention among researchers. Diffusion models (DMs), particularly with strict differential privacy, can potentially produce images with both high privacy and visual quality. However, challenge…
View article: DPFormer: Learning Differentially Private Transformer on Long-Tailed Data
DPFormer: Learning Differentially Private Transformer on Long-Tailed Data Open
The Transformer has emerged as a versatile and effective architecture with broad applications. However, it still remains an open problem how to efficiently train a Transformer model of high utility with differential privacy guarantees. In …
View article: Revisiting Hyperparameter Tuning with Differential Privacy
Revisiting Hyperparameter Tuning with Differential Privacy Open
Hyperparameter tuning is a common practice in the application of machine learning but is a typically ignored aspect in the literature on privacy-preserving machine learning due to its negative effect on the overall privacy parameter. In th…
View article: An Efficient Industrial Federated Learning Framework for AIoT: A Face Recognition Application
An Efficient Industrial Federated Learning Framework for AIoT: A Face Recognition Application Open
Recently, the artificial intelligence of things (AIoT) has been gaining increasing attention, with an intriguing vision of providing highly intelligent services through the network connection of things, leading to an advanced AI-driven eco…