Federated learning is one popular paradigm to train a joint model in a distributed, privacy-preserving environment. But partial annotations pose an obstacle meaning that categories of labels are heterogeneous over clients. We propose to learn a joint backbone in a federated manner, while each site receives its own multi-label segmentation head. By using Bayesian techniques we observe that the different segmentation heads although only trained on the individual client's labels also learn information about the other labels not present at the respective site. This information is encoded in their predictive uncertainty. To obtain a final prediction we leverage this uncertainty and perform a weighted averaging of the ensemble of distributed segmentation heads, which allows us to segment "locally unknown" structures. With our method, which we refer to as FUNAvg, we are even on-par with the models trained and tested on the same dataset on average. The code is publicly available at https://github.com/Cardio-AI/FUNAvg.

翻译：联邦学习是一种在分布式、隐私保护环境中训练联合模型的流行范式。然而，部分标注问题构成了一个障碍，即标签类别在不同客户端间存在异质性。我们提出以联邦方式学习一个联合骨干网络，同时每个站点接收其自身的多标签分割头部。通过使用贝叶斯技术，我们观察到不同的分割头部尽管仅在各自客户端的标签上进行训练，也能学习到其他站点未出现的标签信息。这些信息编码在其预测不确定性中。为获得最终预测，我们利用这种不确定性对分布式分割头部集合进行加权平均，从而能够分割“局部未知”的结构。使用我们称为FUNAvg的方法，我们的模型平均性能甚至与在同一数据集上训练和测试的模型相当。代码已在https://github.com/Cardio-AI/FUNAvg公开提供。