Federated learning (FL) is an active area of research. One of the most suitable areas for adopting FL is the medical domain, where patient privacy must be respected. Previous research, however, does not fully consider who will most likely use FL in the medical domain. It is not the hospitals who are eager to adopt FL, but the service providers such as IT companies who want to develop machine learning models with real patient records. Moreover, service providers would prefer to focus on maximizing the performance of the models at the lowest cost possible. In this work, we propose empirical benchmarks of FL methods considering both performance and monetary cost with three real-world datasets: electronic health records, skin cancer images, and electrocardiogram datasets. We also propose Federated learning with Proximal regularization eXcept local Normalization (FedPxN), which, using a simple combination of FedProx and FedBN, outperforms all other FL algorithms while consuming only slightly more power than the most power efficient method.

翻译：联邦学习(FL)是一个活跃的研究领域。 采用FL最合适的领域之一是医疗领域,病人隐私必须得到尊重。 但是,以前的研究并没有充分考虑到在医疗领域谁最可能使用FL。 不是医院急于采用FL,而是服务供应商,如IT公司,他们希望开发机器学习模型,记录真正的病人记录。此外,服务供应商更愿意侧重于尽可能以最低的成本最大限度地发挥模型的性能。在这项工作中,我们提出了FL方法的经验基准,既考虑性能成本,也考虑货币成本,同时考虑三个真实世界数据集:电子健康记录、皮肤癌图像和电动心电图数据集。我们还提议采用Proximal 正规化电子Xmept 本地正常化(FedPxN), 使用FedProx和FedBN的简单组合,它们超越了所有其他FL算法,同时只消耗比最有效方法略高的功率。