Federated Learning via Over-the-Air Computation

TL;DR

This paper introduces an over-the-air computation method for federated learning that leverages wireless channel superposition to efficiently aggregate models, reducing communication bottlenecks in privacy-sensitive, resource-limited edge devices.

Contribution

It proposes a novel over-the-air aggregation approach using joint device selection and beamforming, modeled as a sparse and low-rank optimization problem with a new DC algorithm.

Findings

Enhanced aggregation efficiency demonstrated through numerical results

Effective device selection and beamforming achieved with the proposed optimization method

Significant reduction in communication latency for federated learning

Abstract

The stringent requirements for low-latency and privacy of the emerging high-stake applications with intelligent devices such as drones and smart vehicles make the cloud computing inapplicable in these scenarios. Instead, edge machine learning becomes increasingly attractive for performing training and inference directly at network edges without sending data to a centralized data center. This stimulates a nascent field termed as federated learning for training a machine learning model on computation, storage, energy and bandwidth limited mobile devices in a distributed manner. To preserve data privacy and address the issues of unbalanced and non-IID data points across different devices, the federated averaging algorithm has been proposed for global model aggregation by computing the weighted average of locally updated model at each selected device. However, the limited communication bandwidth becomes the main bottleneck for aggregating the locally computed updates. We thus propose a novel over-the-air computation based approach for fast global model aggregation via exploring the superposition property of a wireless multiple-access channel. This is achieved by joint device selection and beamforming design, which is modeled as a sparse and low-rank optimization problem to support efficient algorithms design. To achieve this goal, we provide a difference-of-convex-functions (DC) representation for the sparse and low-rank function to enhance sparsity and accurately detect the fixed-rank constraint in the procedure of device selection. A DC algorithm is further developed to solve the resulting DC program with global convergence guarantees. The algorithmic advantages and admirable performance of the proposed methodologies are demonstrated through extensive numerical results.