Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning

TL;DR

This paper introduces a massive digital AirComp scheme that enhances communication efficiency and compatibility for federated edge learning by leveraging vector quantization, shared codebooks, and an approximate message passing algorithm, significantly accelerating convergence.

Contribution

It proposes a novel massive digital AirComp scheme using vector quantization and shared codebooks, with a near-optimal decoding algorithm, improving FEEL convergence and compatibility with digital networks.

Findings

Significantly accelerates FEEL convergence.

Reduces uplink communication overhead.

Enhances compatibility with digital communication networks.

Abstract

Over-the-air computation (AirComp) is a promising technology converging communication and computation over wireless networks, which can be particularly effective in model training, inference, and more emerging edge intelligence applications. AirComp relies on uncoded transmission of individual signals, which are added naturally over the multiple access channel thanks to the superposition property of the wireless medium. Despite significantly improved communication efficiency, how to accommodate AirComp in the existing and future digital communication networks, that are based on discrete modulation schemes, remains a challenge. This paper proposes a massive digital AirComp (MD-AirComp) scheme, that leverages an unsourced massive access protocol, to enhance compatibility with both current and next-generation wireless networks. MD-AirComp utilizes vector quantization to reduce the uplink communication overhead, and employs shared quantization and modulation codebooks. At the receiver, we propose a near-optimal approximate message passing-based algorithm to compute the model aggregation results from the superposed sequences, which relies on estimating the number of devices transmitting each code sequence, rather than trying to decode the messages of individual transmitters. We apply MD-AirComp to the federated edge learning (FEEL), and show that it significantly accelerates FEEL convergence compared to state-of-the-art while using the same amount of communication resources. To support further research and ensure reproducibility, we have made our code available at https://github.com/liqiao19/MD-AirComp.