Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?

TL;DR

This paper investigates whether sparsification is necessary in Over-the-Air Federated Learning with compressed sensing, finding that sparsification before compression is not essential and can sometimes be less effective.

Contribution

The study compares communication strategies with and without sparsification, revealing that sparsification is not required for effective compressed sensing in OtA FL.

Findings

Sparsification before compression is unnecessary.

Linear compression with CS can outperform sparsified transmission.

Direct transmission of non-zero elements can be more effective.

Abstract

Over-the-Air (OtA) Federated Learning (FL) refers to an FL system where multiple agents apply OtA computation for transmitting model updates to a common edge server. Two important features of OtA computation, namely linear processing and signal-level superposition, motivate the use of linear compression with compressed sensing (CS) methods to reduce the number of data samples transmitted over the channel. The previous works on applying CS methods in OtA FL have primarily assumed that the original model update vectors are sparse, or they have been sparsified before compression. However, it is unclear whether linear compression with CS-based reconstruction is more effective than directly sending the non-zero elements in the sparsified update vectors, under the same total power constraint. In this study, we examine and compare several communication designs with or without sparsification. Our findings demonstrate that sparsification before compression is not necessary. Alternatively, sparsification without linear compression can also achieve better performance than the commonly considered setup that combines both.