Federated learning is a collaborative model training method by iterating model updates at multiple clients and aggregation of the updates at a central server. Device and statistical heterogeneity of the participating clients cause performance degradation so that an appropriate weight should be assigned per client in the server's aggregation phase. This paper employs deep unfolding to learn the weights that adapt to the heterogeneity, which gives the model with high accuracy on uniform test data. The results of numerical experiments indicate the high performance of the proposed method and the interpretable behavior of the learned weights.

翻译：联邦学习是一种合作示范培训方法,在多个客户中反复更新模型更新,并在中央服务器中汇总更新内容。参加学习的客户的设备和统计差异导致性能退化,因此在服务器汇总阶段,每个客户应分配适当的权重。本文利用深度发展来学习适应异质的权重,使模型在统一测试数据中具有高度精确性。数字实验的结果显示拟议方法的高度性能和可解释的权重行为。