Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting a Gaussian or Dirichlet distribution to the local models. Our empirical studies validate FedBE's superior performance, especially when users' data are not i.i.d. and when the neural networks go deeper. Moreover, FedBE is compatible with recent efforts in regularizing users' model training, making it an easily applicable module: you only need to replace the aggregation method but leave other parts of your federated learning algorithm intact. Our code is publicly available at https://github.com/hongyouc/FedBE.
翻译:联邦学习的目的是通过访问用户在当地培训的模型,而不是他们自己的数据,合作训练一个强大的全球模型。因此,一个关键步骤是将当地模型合并成一个全球模型,当用户拥有非i.i.d.数据时,这一模型就具有挑战性。在本文中,我们提议采用名为FedBE的新综合算法,采用巴伊西亚推论的观点,通过抽样比较高质量的全球模型,并把它们结合到巴伊西亚模型中,从而形成非常有力的聚合。我们表明,只要将高斯或迪里赫莱特的分布与当地模型相匹配,就可以构建一个有效的模型分布。我们的经验研究验证了FedBE的高级性能,特别是当用户的数据不是i.i.d.和神经网络更深的时候。此外,FedBE与最近使用户模型培训正规化的努力相匹配,使其成为一个易于应用的模块:你只需要替换汇总方法,而使你的节化学习算法的其他部分保持不变。我们的代码可以在https://github.com/hongyooyouc/FedBE公开查阅。