We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Utility Optimization of Federated Learning with Differential Privacy.
- Authors
Zhao, Jianzhe; Mao, Keming; Huang, Chenxi; Zeng, Yuyang
- Abstract
Secure and trusted cross-platform knowledge sharing is significant for modern intelligent data analysis. To address the trade-off problems between privacy and utility in complex federated learning, a novel differentially private federated learning framework is proposed. First, the impact of data heterogeneity of participants on global model accuracy is analyzed quantitatively based on 1-Wasserstein distance. Then, we design a multilevel and multiparticipant dynamic allocation method of privacy budget to reduce the injected noise, and the utility can be improved efficiently. Finally, they are integrated, and a novel adaptive differentially private federated learning algorithm (A-DPFL) is designed. Comprehensive experiments on redefined non-I.I.D MNIST and CIFAR-10 datasets are conducted, and the results demonstrate the superiority of model accuracy, convergence, and robustness.
- Subjects
PRIVACY; MACHINE learning; INFORMATION sharing; DATA analysis
- Publication
Discrete Dynamics in Nature & Society, 2021, p1
- ISSN
1026-0226
- Publication type
Article
- DOI
10.1155/2021/3344862