Federated learning allows multiple parties to collaboratively train a joint model without sharing local data. This enables applications of machine learning in settings of inherently distributed, undisclosable data such as in the medical domain. In practice, joint training is usually achieved by aggregating local models, for which local training objectives have to be in expectation similar to the joint (global) objective. Often, however, local datasets are so small that local objectives differ greatly from the global objective, resulting in federated learning to fail. We propose a novel approach that intertwines model aggregations with permutations of local models. The permutations expose each local model to a daisy chain of local datasets resulting in more efficient training in data-sparse domains. This enables training on extremely small local datasets, such as patient data across hospitals, while retaining the training efficiency and privacy benefits of federated learning.

翻译：联邦学习允许多方在不共享本地数据的情况下协作训练联合模型，这使得在医学领域等固有分布式且不可公开的数据场景中应用机器学习成为可能。实践中，联合训练通常通过聚合局部模型来实现，这要求局部训练目标在期望意义上与联合（全局）目标相近。然而，本地数据集往往规模过小，导致局部目标与全局目标差异显著，进而使联邦学习失效。我们提出了一种新方法，在模型聚集中交织局部模型的排列操作。排列操作使每个局部模型依次接触一系列本地数据集，形成"雏菊链"式数据流，从而在数据稀疏领域实现更高效的训练。该方法能够在极小的本地数据集（如医院间的患者数据）上开展训练，同时保留联邦学习的训练效率与隐私保护优势。