用超梯度在线调整权重，让联邦学习更适应设备差异和网络波动。
Federated Learning with Hypergradient-based Online Update of Aggregation Weights
- 基于超梯度动态调整客户端权重，计算开销低。
- 在数据异构环境下表现优异，通信错误下仍保持稳定。
- 适合边缘设备、物联网等不稳定通信场景使用。
基于移动设备和物联网的联邦学习不仅需应对客户端数据分布的异构性，还需适应变化的通信环境。本文提出 FedHAW（基于超梯度更新聚合权重的联邦学习），实现聚合权重的在线更新。该方法利用超梯度——即目标函数对权重的梯度——进行更新，具有较低的计算开销。仿真结果表明，所提方法在异构环境下具备高泛化性能，并对通信错误具有强鲁棒性。
原文摘要 · Abstract (English)
Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but also high adaptability to varying communication environments. We propose FedHAW (Federated Learning with Hypergradient-based update of Aggregation Weights) that implements online updates of aggregation weights. FedHAW updates the aggregation weights by using hypergradient, the gradient of the objective function with respect to the weights, which can be calculated with low computational overhead. Simulation results show that the proposed method possesses high generalization performance in heterogeneous environments and high robustness to communication errors.
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。