Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices
This addresses privacy and efficiency challenges for edge device applications requiring rapid convergence, though it is incremental as it builds on existing federated learning methods.
The paper tackles the issues of latency and degraded model performance in federated learning due to network topology, physical distance, and data heterogeneity on edge devices by proposing FedEDS, which uses encrypted data sharing to accelerate convergence and mitigate data heterogeneity, with experiments showing improved model performance.
As privacy protection gains increasing importance, more models are being trained on edge devices and subsequently merged into the central server through Federated Learning (FL). However, current research overlooks the impact of network topology, physical distance, and data heterogeneity on edge devices, leading to issues such as increased latency and degraded model performance. To address these issues, we propose a new federated learning scheme on edge devices that called Federated Learning with Encrypted Data Sharing(FedEDS). FedEDS uses the client model and the model's stochastic layer to train the data encryptor. The data encryptor generates encrypted data and shares it with other clients. The client uses the corresponding client's stochastic layer and encrypted data to train and adjust the local model. FedEDS uses the client's local private data and encrypted shared data from other clients to train the model. This approach accelerates the convergence speed of federated learning training and mitigates the negative impact of data heterogeneity, making it suitable for application services deployed on edge devices requiring rapid convergence. Experiments results show the efficacy of FedEDS in promoting model performance.