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

arXiv: https://arxiv.org/abs/2506.05411 · HTML: https://mlsanity.com/paper/2506.05411/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction](https://mlsanity.com/paper/2212.01548/) (2022)
- [FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization](https://mlsanity.com/paper/2111.14655/) (2021)
- [AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems](https://mlsanity.com/paper/2311.13166/) (2023)
- [AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems](https://mlsanity.com/paper/2311.14037/) (2023)
- [HierSFL: Local Differential Privacy-aided Split Federated Learning in Mobile Edge Computing](https://mlsanity.com/paper/2401.08723/) (2024)
- [HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation](https://mlsanity.com/paper/2212.02006/) (2022)
- [ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation](https://mlsanity.com/paper/2311.11083/) (2023)

## Abstract (arXiv)

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.