Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
This work addresses scalability and efficiency issues in federated learning for large-scale deployments like smartphones and IoT devices, though it appears incremental as it builds on existing federated learning frameworks.
The authors tackled the communication bottlenecks and waiting times in synchronous federated learning by proposing an asynchronous algorithm that reduces network rounds and adds differential privacy with less aggregated Gaussian noise, achieving theoretical guarantees for strongly convex functions and demonstrating results through simulations.
The feasibility of federated learning is highly constrained by the server-clients infrastructure in terms of network communication. Most newly launched smartphones and IoT devices are equipped with GPUs or sufficient computing hardware to run powerful AI models. However, in case of the original synchronous federated learning, client devices suffer waiting times and regular communication between clients and server is required. This implies more sensitivity to local model training times and irregular or missed updates, hence, less or limited scalability to large numbers of clients and convergence rates measured in real time will suffer. We propose a new algorithm for asynchronous federated learning which eliminates waiting times and reduces overall network communication - we provide rigorous theoretical analysis for strongly convex objective functions and provide simulation results. By adding Gaussian noise we show how our algorithm can be made differentially private -- new theorems show how the aggregated added Gaussian noise is significantly reduced.