针对手机端图像质量差异，提出智能分层联邦学习框架。
QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality
- 按图像质量分级训练本地模型，用质量加权融合特征
- 3轮通信达92.31%准确率，隐私保护下仍保持30.77%性能
- 低配设备贡献63.5%，适合资源受限的移动端应用
本文提出QA-HFL，一种面向资源受限移动设备的感知图像质量分层联邦学习框架，有效处理设备间图像质量异构问题。通过为不同图像质量级别训练专用本地模型，并采用质量加权融合机制聚合特征，同时集成差分隐私保护。在MNIST数据集上，仅经三轮联邦通信即达92.31%准确率，显著优于当前最优方法FedRolex（86.42%）。在严格隐私约束下，仍保持30.77%准确率并满足正式差分隐私保障。反直觉的是，低性能设备虽比高性能设备少用100参数，却贡献了63.5%的模型提升。该方法通过设备特定正则化、自适应加权、智能客户端选择及服务器端知识蒸馏，缓解精度下降问题，同时实现4.71%的通信压缩比。统计分析表明，在标准与隐私约束条件下，本方法均显著优于基线（p < 0.01）。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。