We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether learning over data sets that do not have diverse sets of images affects the results; whether to use a pre-trained feature extraction "backbone"; how to evaluate learner performance (we argue that classification accuracy is not enough), among others. Overall, across a wide variety of settings, we find that vertically decomposing a neural network seems to give the best results, and outperforms more standard reconciliation-used methods.

翻译：我们仔细评估了若干适用于联邦学习环境的算法，并在多种图像分类任务中测试其有效性。我们系统考察了先前研究未充分关注的多个关键问题：在缺乏图像多样性的数据集上进行学习是否影响结果；是否应使用预训练特征提取"骨干网络"；如何合理评估学习器性能（我们论证了仅凭分类准确率不足以全面衡量）等。综合各类实验设置，我们发现对神经网络进行垂直分解通常能取得最佳效果，且优于更传统的协同训练方法。