面向样本级客户端漂移缓解的联邦学习

联邦学习（FL）因客户端之间的数据异构性而遭受严重的性能下降。已有研究揭示，其根本原因在于数据异构性可导致客户端漂移，即本地模型更新偏离全局模型，因而通常从校准获取的本地更新的角度来解决此问题。尽管有效，但现有方法在深入理解异构数据样本如何贡献于客户端漂移形成方面 substantially 缺乏认识。在本文中，我们填补了这一鸿沟，通过表明漂移可被视为所有本地样本中偏差的累积表现，样本之间的偏差不同。此外，随着FL训练的进行，偏差会动态变化。ederated our method is to first mitigate the heterogeneity issue in a sample-level manner, orthogonal to existing methods. Specifically, the core idea of our method is to adopt a bias-aware sample selection scheme that dynamically selects the samples from small biases to large epoch by epoch to train progressively the local model in each round. In order to ensure the stability of training, we set the diversified knowledge acquisition stage as the warm-up stage to avoid the local optimality caused by knowledge deviation in the early stage of the model. Evaluation results show that FedBSS outperforms state-of-the-art baselines. In addition, we also achieved effective results on feature distribution skew and noise label dataset setting, which proves that FedBSS can not only reduce heterogeneity, but also has scalability and robustness.