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

2025/06/04 by Muhammad Sohail, Hussain, Sajid, Sohail, Muhammad +2
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Image and Video Quality Assessment #IoT and Edge/Fog Computing #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2506.05411

openalex publication_date 2025/06/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing
• AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems
• ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation
• HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
• FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
• FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization

Related

• REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments
• H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning
• Evaluating the Communication Efficiency in Federated Learning Algorithms
• FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning
• Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks