Adaptive Gradient Methods For Over-the-Air Federated Learning

Federated learning (FL) provides a privacy-preserving approach to realizing networked intelligence. However, the performance of FL is often constrained by the limited communication resources, especially in the context of a wireless system. To tackle this communication bottleneck, recent studies propose an analog over-the-air (A-OTA) FL paradigm which employs A-OTA computations in the model aggregation step that significantly enhances scalability. The existing architectures mainly conduct model training via (stochastic) gradient descent, while adaptive optimization methods, which have achieved notable success in deep learning, remain unexplored. In this paper, we establish a distributed training paradigm that incorporates adaptive gradient methods into the A-OTA FL framework, aiming to enhance the system’s convergence performance. We derive an analytical expression for the convergence rate, capturing the effects of various system parameters on the convergence performance of the proposed method. We also perform several experiments to validate the efficacy of the proposed method.