Blind Federated Learning at the Wireless Edge with Low-Resolution ADC and DAC

TL;DR

This paper investigates federated learning over wireless channels with low-resolution DACs and ADCs, showing that low-cost hardware impairments minimally impact convergence and accuracy when using multiple antennas.

Contribution

It provides a theoretical analysis demonstrating that low-resolution DACs and ADCs do not hinder federated learning convergence, especially with multiple antennas at the parameter server.

Findings

Low-resolution DACs and ADCs cause minimal accuracy loss.

Multiple antennas mitigate channel impairments.

Convergence is maintained despite hardware limitations.

Abstract

We study collaborative machine learning systems where a massive dataset is distributed across independent workers which compute their local gradient estimates based on their own datasets. Workers send their estimates through a multipath fading multiple access channel with orthogonal frequency division multiplexing to mitigate the frequency selectivity of the channel. We assume that there is no channel state information (CSI) at the workers, and the parameter server (PS) employs multiple antennas to align the received signals. To reduce the power consumption and the hardware costs, we employ complex-valued low-resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs), at the transmitter and the receiver sides, respectively, and study the effects of practical low-cost DACs and ADCs on the learning performance. Our theoretical analysis shows that the impairments caused by low-resolution DACs and ADCs, including those of one-bit DACs and ADCs, do not prevent the convergence of the federated learning algorithm, and the multipath channel effects vanish when a sufficient number of antennas are used at the PS. We also validate our theoretical results via simulations, and demonstrate that using low-resolution, even one-bit, DACs and ADCs causes only a slight decrease in the learning accuracy.