Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy

no code implementations • 18 Aug 2022 • Wenqiang Ruan, Mingxin Xu, Wenjing Fang, Li Wang, Lei Wang, Weili Han

Second, to reduce the accuracy loss led by differential privacy noise and the huge communication overhead of MPL, we propose two optimization methods for the training process of MPL: (1) the data-independent feature extraction method, which aims to simplify the trained model structure; (2) the local data-based global model initialization method, which aims to speed up the convergence of the model training.

SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation

no code implementations • 6 Dec 2020 • Lushan Song, Guopeng Lin, Jiaxuan Wang, Haoqi Wu, Wenqiang Ruan, Weili Han

At first, we define the problem of Training machine learning Models over Multiple data sources with Privacy Preservation (TMMPP for short).

BIG-bench Machine Learning Federated Learning +1