联邦子模型学习（FSL）中的私有读更新写（PRUW）：有和没有稀疏化的通信有效方案
Private Read Update Write (PRUW) in Federated Submodel Learning (FSL): Communication Efficient Schemes With and Without Sparsification
摘要：
我们研究了与私有联邦子模型学习（FSL）相关的私有读更新写（PRUW）问题，其中机器学习模型根据用于训练模型的不同类型的数据被划分为多个子模型。在PRUW中，每个用户在读取阶段下载所需的子模型而不显示其索引，并在写入阶段上传子模型的更新而不显示子模型索引或更新的值。在这项工作中，我们首先提供了一个基本的通信效率PRUW计划，并研究通过稀疏化进一步降低通信成本的手段。梯度稀疏化是学习应用中广泛使用的概念，其中仅下载和更新选定的一组参数，这显著降低了通信成本。在本文中，我们研究如何稀疏化的概念可以被纳入私人FSL的目标是降低通信成本，同时保证信息理论的隐私更新的子模型索引以及更新的值。为此，我们介绍了两种方案：PRUW与顶部$r$稀疏和PRUW与随机稀疏。前者仅在服务器和用户之间传送最重要的参数/更新，而后者传送随机选择的参数/更新集。这两个建议的计划引入了新的技术，如参数/更新（噪声）置换处理的额外来源的信息泄漏在PRUW所造成的稀疏化。这两种方案的结果显着降低通信成本相比，基本（非稀疏）PRUW计划。
英文摘要：
We investigate the problem of private read update write (PRUW) in relation to private federated submodel learning (FSL), where a machine learning model is divided into multiple submodels based on the different types of data used to train the model. In PRUW, each user downloads the required submodel without revealing its index in the reading phase, and uploads the updates of the submodel without revealing the submodel index or the values of the updates in the writing phase. In this work, we first provide a basic communication efficient PRUW scheme, and study further means of reducing the communication cost via sparsification. Gradient sparsification is a widely used concept in learning applications, where only a selected set of parameters is downloaded and updated, which significantly reduces the communication cost. In this paper, we study how the concept of sparsification can be incorporated in private FSL with the goal of reducing the communication cost, while guaranteeing information theoretic privacy of the updated submodel index as well as the values of the updates. To this end, we introduce two schemes: PRUW with top $r$ sparsification and PRUW with random sparsification. The former communicates only the most significant parameters/updates among the servers and the users, while the latter communicates a randomly selected set of parameters/updates. The two proposed schemes introduce novel techniques such as parameter/update (noisy) permutations to handle the additional sources of information leakage in PRUW caused by sparsification. Both schemes result in significantly reduced communication costs compared to that of the basic (non-sparse) PRUW scheme.
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。
