Search Results for author:
Found 6 papers, 1 papers with code
The Effect of Quantization in Federated Learning: A Rényi Differential Privacy Perspective
To enhance privacy, FL can be combined with Differential Privacy (DP), which involves adding Gaussian noise to the model weights.
Binary Federated Learning with Client-Level Differential Privacy
To improve communication efficiency and achieve a better privacy-utility trade-off, we propose a communication-efficient FL training algorithm with differential privacy guarantee.
A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
Without data centralization, FL allows clients to share local information in a privacy-preserving manner.
Communication-Efficient Federated Distillation with Active Data Sampling
Federated Distillation (FD) is a recently proposed alternative to enable communication-efficient and robust FL, which achieves orders of magnitude reduction of the communication overhead compared with FedAvg and is flexible to handle heterogeneous models at the clients.
Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design
Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server's access to many clients' data and the edge servers' closeness to the clients to achieve a high communication efficiency.
Client-Edge-Cloud Hierarchical Federated Learning
To combine their advantages, we propose a client-edge-cloud hierarchical Federated Learning system, supported with a HierFAVG algorithm that allows multiple edge servers to perform partial model aggregation.
