Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control

TL;DR

This paper introduces ACPC-OTA-FL, a novel over-the-air federated learning method that adaptively manages power and computation to mitigate channel noise, achieving convergence rates comparable to noiseless FL.

Contribution

It presents a joint adaptive power and computation control scheme for OTA-FL, with theoretical analysis and convergence guarantees under realistic wireless conditions.

Findings

Achieves convergence rate similar to noiseless FL.

Provides a fundamental lower bound on training error due to channel noise.

Introduces an adaptive transceiver scheme for improved OTA-FL performance.

Abstract

This paper considers over-the-air federated learning (OTA-FL). OTA-FL exploits the superposition property of the wireless medium, and performs model aggregation over the air for free. Thus, it can greatly reduce the communication cost incurred in communicating model updates from the edge devices. In order to fully utilize this advantage while providing comparable learning performance to conventional federated learning that presumes model aggregation via noiseless channels, we consider the joint design of transmission scaling and the number of local iterations at each round, given the power constraint at each edge device. We first characterize the training error due to such channel noise in OTA-FL by establishing a fundamental lower bound for general functions with Lipschitz-continuous gradients. Then, by introducing an adaptive transceiver power scaling scheme, we propose an over-the-air federated learning algorithm with joint adaptive computation and power control (ACPC-OTA-FL). We provide the convergence analysis for ACPC-OTA-FL in training with non-convex objective functions and heterogeneous data. We show that the convergence rate of ACPC-OTA-FL matches that of FL with noise-free communications.