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.