QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality

TL;DR

QA-HFL introduces a hierarchical federated learning framework that adapts to heterogeneous image quality on resource-limited mobile devices, achieving high accuracy with privacy guarantees and efficient communication.

Contribution

It presents a novel quality-aware hierarchical federated learning approach with specialized local models, quality-weighted fusion, and privacy protection, outperforming existing methods.

Findings

Achieves 92.31% accuracy after three rounds on MNIST

Maintains 30.77% accuracy under differential privacy constraints

Low-end devices contribute significantly despite fewer parameters

Abstract

This paper introduces QA-HFL, a quality-aware hierarchical federated learning framework that efficiently handles heterogeneous image quality across resource-constrained mobile devices. Our approach trains specialized local models for different image quality levels and aggregates their features using a quality-weighted fusion mechanism, while incorporating differential privacy protection. Experiments on MNIST demonstrate that QA-HFL achieves 92.31% accuracy after just three federation rounds, significantly outperforming state-of-the-art methods like FedRolex (86.42%). Under strict privacy constraints, our approach maintains 30.77% accuracy with formal differential privacy guarantees. Counter-intuitively, low-end devices contributed most significantly (63.5%) to the final model despite using 100 fewer parameters than high-end counterparts. Our quality-aware approach addresses accuracy decline through device-specific regularization, adaptive weighting, intelligent client selection, and server-side knowledge distillation, while maintaining efficient communication with a 4.71% compression ratio. Statistical analysis confirms that our approach significantly outperforms baseline methods (p 0.01) under both standard and privacy-constrained conditions.