FL-MAC-RDP: Federated Learning over Multiple Access Channels with Rényi Differential Privacy
Autor: | Yaguan Qian, Mengqing Yu, Yuanhong Tao, Moushira Abdallah Mohamed Ahmed, Shu-Hui Wu |
---|---|
Rok vydání: | 2021 |
Předmět: |
Scheme (programming language)
Physics and Astronomy (miscellaneous) Third party Computer science business.industry General Mathematics Process (computing) Federated learning Stochastic gradient descent Differential privacy business Quantization (image processing) computer MNIST database Computer network computer.programming_language |
Zdroj: | International Journal of Theoretical Physics. 60:2668-2682 |
ISSN: | 1572-9575 0020-7748 |
Popis: | Federated Learning (FL) is a promising paradigm, where the local users collaboratively learn models by repeatedly sharing information while the data is kept distributing on these users. FL has been considered in multiple access channels (FL-MAC), which is a hot issue. Even though FL-MAC has many advantages, it is still possible to leak privacy to a third party during the whole training process. To avoid privacy leakage, we propose to add Renyi differential privacy (RDP) into FL-MAC. At the same time, to maximize the convergent rate of users under the constraints of transmission rate and privacy, the quantization stochastic gradient descent (QSGD) is performed by users. We also illustrate our results on MNIST, and the illustration demonstrate that our scheme can improve the model accuracy with a little loss of communication efficiency. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |