PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learning
This work addresses communication efficiency for federated learning systems, offering a low-complexity solution that is incremental over existing compressed sensing methods.
The paper tackles the problem of reducing communication overhead in federated learning over noisy channels by proposing PolarAir, a compressed sensing scheme that compresses gradients to lower channel usage. Simulations show it reduces channel uses by approximately 30% compared to uncompressed transmission.
We explore a scheme that enables the training of a deep neural network in a Federated Learning configuration over an additive white Gaussian noise channel. The goal is to create a low complexity, linear compression strategy, called PolarAir, that reduces the size of the gradient at the user side to lower the number of channel uses needed to transmit it. The suggested approach belongs to the family of compressed sensing techniques, yet it constructs the sensing matrix and the recovery procedure using multiple access techniques. Simulations show that it can reduce the number of channel uses by ~30% when compared to conveying the gradient without compression. The main advantage of the proposed scheme over other schemes in the literature is its low time complexity. We also investigate the behavior of gradient updates and the performance of PolarAir throughout the training process to obtain insight on how best to construct this compression scheme based on compressed sensing.