Recently, Niu, et. al. introduced a new variant of Federated Learning (FL), called Federated Submodel Learning (FSL). Different from traditional FL, each client locally trains the submodel (e.g., retrieved from the servers) based on its private data and uploads a submodel at its choice to the servers. Then all clients aggregate all their submodels and finish the iteration. Inevitably, FSL introduces two privacy-preserving computation tasks, i.e., Private Submodel Retrieval (PSR) and Secure Submodel Aggregation (SSA). Existing work fails to provide a loss-less scheme, or has impractical efficiency. In this work, we leverage Distributed Point Function (DPF) and cuckoo hashing to construct a practical and light-weight secure FSL scheme in the two-server setting. More specifically, we propose two basic protocols with few optimisation techniques, which ensures our protocol practicality on specific real-world FSL tasks. Our experiments show that our proposed protocols can finish in less than 1 minute when weight sizes $\leq 2^{15}$, we also demonstrate protocol efficiency by comparing with existing work and by handling a real-world FSL task.

翻译：最近,Niu等人提出了一个新的联邦学习(FL)新变体,称为Federed Submodel Learning(FSL) 。与传统的FL不同,每个客户都根据私人数据在当地培训子模型(例如从服务器上检索),然后根据自己的个人数据将一个子模型上传到服务器上,然后所有客户将其所有子模型集中起来,完成迭代。毫无疑问,FSL引入了两种隐私保护计算任务,即私人子模型Retreriewval(PSR)和安全子模型聚合(SSA)。现有的工作无法提供无损计划,或者效率不切实际。在这项工作中,我们利用分布点功能(DPF)和库库在两个服务器的设置中,建立一个实用和轻度安全的FSL计划。更具体地说,我们提出了两个基本协议,采用很少的优化技术,确保我们的协议在具体的现实世界FSL任务上具有实用性。我们的实验表明,当重量大小为$\leq 2 ⁇ 15美元时,我们提议的协议可以在不到1分钟内完成,而现有的协议通过实际操作效率比FSFS-L任务。