Enhancing Privacy via Hierarchical Federated Learning
This work addresses privacy threats for participants in federated learning systems, but it appears incremental as it builds on existing hierarchical approaches without presenting new experimental results.
The paper tackles privacy issues in federated learning by proposing a hierarchical architecture, which offers more flexible decentralized control and potential enhancements in defense and verification methods.
Federated learning suffers from several privacy-related issues that expose the participants to various threats. A number of these issues are aggravated by the centralized architecture of federated learning. In this paper, we discuss applying federated learning on a hierarchical architecture as a potential solution. We introduce the opportunities for more flexible decentralized control over the training process and its impact on the participants' privacy. Furthermore, we investigate possibilities to enhance the efficiency and effectiveness of defense and verification methods.