Constrained Differentially Private Federated Learning for Low-bandwidth Devices
This addresses privacy and bandwidth constraints for low-bandwidth devices like mobile systems, offering an incremental improvement over existing federated learning approaches.
The paper tackles the bandwidth inefficiency and privacy leakage issues in federated learning by proposing a differentially private scheme that constrains learning to selected weights, reducing bandwidth by up to 99.9% compared to standard methods.
Federated learning becomes a prominent approach when different entities want to learn collaboratively a common model without sharing their training data. However, Federated learning has two main drawbacks. First, it is quite bandwidth inefficient as it involves a lot of message exchanges between the aggregating server and the participating entities. This bandwidth and corresponding processing costs could be prohibitive if the participating entities are, for example, mobile devices. Furthermore, although federated learning improves privacy by not sharing data, recent attacks have shown that it still leaks information about the training data. This paper presents a novel privacy-preserving federated learning scheme. The proposed scheme provides theoretical privacy guarantees, as it is based on Differential Privacy. Furthermore, it optimizes the model accuracy by constraining the model learning phase on few selected weights. Finally, as shown experimentally, it reduces the upstream and downstream bandwidth by up to 99.9% compared to standard federated learning, making it practical for mobile systems.