Computation- and Communication-Efficient Online FL for Resource-Constrained Aerial Vehicles

TL;DR

This paper introduces a novel online federated learning algorithm tailored for resource-constrained aerial vehicles, enabling efficient data processing and model updates through pruning and quantization techniques, while maintaining high performance.

Contribution

The paper proposes the 2CEOAFL algorithm that combines model pruning and gradient quantization for resource-efficient online federated learning in aerial vehicles.

Findings

Achieves comparable accuracy to traditional methods with reduced computation and communication.

Effectively models ACV trajectories based on their data distributions.

Demonstrates significant efficiency improvements in simulations.

Abstract

Privacy-preserving distributed machine learning (ML) and aerial connected vehicle (ACV)-assisted edge computing have drawn significant attention lately. Since the onboard sensors of ACVs can capture new data as they move along their trajectories, the continual arrival of such 'newly' sensed data leads to online learning and demands carefully crafting the trajectories. Besides, as typical ACVs are inherently resource-constrained, computation- and communication-efficient ML solutions are needed. Therefore, we propose a computation- and communication-efficient online aerial federated learning (2CEOAFL) algorithm to take the benefits of continual sensed data and limited onboard resources of the ACVs. In particular, considering independently owned ACVs act as selfish data collectors, we first model their trajectories according to their respective time-varying data distributions. We then propose a 2CEOAFL algorithm that allows the flying ACVs to (a) prune the received dense ML model to make it shallow, (b) train the pruned model, and (c) probabilistically quantize and offload their trained accumulated gradients to the central server (CS). Our extensive simulation results show that the proposed 2CEOAFL algorithm delivers comparable performances to its non-pruned and nonquantized, hence, computation- and communication-inefficient counterparts.