Robust Federated Learning Over Noisy Fading Channels

The performance capabilities of models trained in a federated learning (FL) setting over wireless networks can be significantly affected by the underlying properties of the transmission channel. Even for shallow models, there can be an acute degradation in performance which necessitates the development of algorithms which are robust to transmission channel effects, such as noise and fading. In this work, we present a two-pronged approach to overcome the limitations of existing wireless machine learning (ML)-based algorithms. First, to tackle the effect of channel noise, we incorporate a novel tracking-based stochastic approximation scheme in the standard federated averaging pipeline which averages out the effect of the channel noise. In contrast to previous works on FL with a noisy channel, we provide exact convergence guarantees for our algorithm without the need to increase the transmission power gain. Second, to combat channel fading and further optimize the power consumption at the client level, we propose an adaptive transmission policy obtained by solving an optimization problem with long-term constraints. The solution is obtained in an online manner via a dual decomposition method. The superior empirical performance of the proposed scheme compared to state-of-the-art works is demonstrated on standard ML tasks.

Automated summary

The performance of federated learning models in wireless networks can be affected by transmission channel properties. This article proposes a two-pronged approach to address the limitations of current wireless machine learning algorithms. A stochastic approximation scheme is incorporated to mitigate the effect of channel noise, while an adaptive transmission policy is developed to combat channel fading and optimize power consumption. The proposed scheme demonstrates superior performance compared to state-of-the-art works on standard machine learning tasks.