FUNAvg：面向标签多样化数据集的联邦不确定性加权平均
FUNAvg: Federated Uncertainty Weighted Averaging for Datasets with Diverse Labels
AI总结：
针对联邦学习中客户端标签类别异构的部分标注问题，提出FUNAvg方法，通过贝叶斯技术挖掘分割头的预测不确定性，加权平均分布式分割头以分割局部未知结构，性能比肩同数据集训练的模型。
摘要：
联邦学习是在分布式、隐私保护环境下训练联合模型的一种主流范式。但部分标注构成了阻碍，即各客户端的标签类别存在异构性。我们提出以联邦方式学习一个联合骨干网络，同时每个站点配备各自的多标签分割头。通过贝叶斯技术我们观察到，不同的分割头尽管仅在各自客户端的标签上训练，也能学习到对应站点不存在的其他标签的相关信息，这些信息被编码在其预测不确定性中。为得到最终预测，我们利用这种不确定性对分布式分割头的集成结果进行加权平均，从而能够分割“局部未知”的结构。借助我们提出的名为FUNAvg的方法，其平均性能甚至与在相同数据集上训练并测试的模型相当。代码已公开于https://github.com/Cardio-AI/FUNAvg。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
