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

2025-06-03

AI Summary

To address the challenges of online federated learning for resource-constrained aerial computing vehicles (ACVs) operating under time-varying data distributions, selfish node behavior, and severe communication and computational limitations, this paper proposes the first online aerial federated learning framework integrating trajectory-aware modeling, dynamic model pruning, and probabilistic gradient quantization. By jointly modeling ACV mobility trajectories and local data distributions, we design a lightweight pruning strategy to reduce on-device computation, and introduce a probabilistic quantization mechanism to compress uploaded gradients—significantly alleviating bandwidth bottlenecks. An online optimization mechanism further ensures convergence and robustness under non-IID and dynamically shifting data regimes. Experiments demonstrate that our method achieves accuracy comparable to the full-model baseline while reducing model depth by 30% and communication overhead by 65%, thereby enabling, for the first time, timely, low-cost, and privacy-preserving collaborative learning at the aerial edge.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Efficient online federated learning for resource-constrained aerial vehicles
• Privacy-preserving distributed ML with continual data from ACV sensors
• Trajectory optimization for selfish ACVs with time-varying data distributions

Innovation

• Online aerial federated learning algorithm
• Model pruning and shallow training
• Probabilistic gradient quantization and offloading