针对无线异构环境，动态调整聚合时机提升联邦学习精度与稳定性。
Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks
- 根据信道状态和应用就绪度自适应调度聚合时机。
- 在噪声和慢节点场景下，准确率、稳定性和收敛速度显著优于现有方法。
- 适合部署于物联网、6G等高异构性无线网络中的隐私保护应用。
随着物联网、增强现实和自动驾驶等数据密集型隐私保护应用的兴起，联邦学习（FL）成为6G网络的关键使能技术。过空气联邦学习（OTA-FL）利用无线多址信道的叠加特性，通过并发传输实现高效聚合。现有方法依赖固定聚合调度，未能协同应对噪声、信道衰落和客户端异构性问题。本文提出CHARGE-FL（CHannel-Adaptive Robust agGrEgation）框架，基于信道动态和应用就绪度自适应调度聚合。结合定制优化策略与双重用途预编码机制，有效缓解信道失真及部分更新带来的偏差，在真实无线条件下实现更高精度、更强稳定性和更快收敛。实证结果表明，相较于最先进方法，CHARGE-FL在存在慢节点和强噪声的场景中显著提升性能。
原文摘要 · Abstract (English)
The growing demand for privacy-preserving, data-intensive applications such as IoT, augmented reality, and autonomous systems positions Federated Learning (FL) as a key enabler in 6G networks. Over-the-Air FL (OTA-FL) leverages the superposition property of the wireless multiple access channel for efficient aggregation via simultaneous transmissions. Existing methods rely on fixed aggregation schedules and do not jointly address noise, fading, and client heterogeneity. We propose CHARGE-FL (CHannel-Adaptive Robust agGrEgation), a framework that adaptively schedules aggregation based on channel dynamics and application readiness. By combining a tailored optimization strategy with a dual-purpose precoding mechanism, CHARGE-FL mitigates channel distortion and bias from partial updates, achieving superior accuracy, stability, and convergence under realistic wireless conditions. Empirical results under realistic wireless conditions show that CHARGE-FL significantly improves accuracy, stability, and convergence over state-of-the-art OTA-FL methods, particularly in straggler-prone and noisy scenarios.
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。