联邦子模型学习中私有读更新写的率失真折衷
Rate Distortion Tradeoff in Private Read Update Write in Federated Submodel Learning
摘要:
我们调查的率失真权衡私人读更新写(PRUW)联邦子模型学习(FSL)。在FSL中,机器学习(ML)模型基于用于训练的不同类型的数据被划分为多个子模型。每个用户只下载和更新与其本地数据相关的子模型。下载和更新所需的子模型,同时保证子模型索引和更新值的隐私的过程被称为PRUW。在这项工作中,我们研究如何PRUW的通信成本可以降低时,一个预先确定的失真量是允许在读取(下载)和写入(上传)阶段。我们的特点率失真权衡PRUW随着一个计划,实现了最低的通信成本,同时在给定的失真预算下工作。
英文摘要:
We investigate the rate distortion tradeoff in private read update write (PRUW) in relation to federated submodel learning (FSL). In FSL a machine learning (ML) model is divided into multiple submodels based on different types of data used for training. Each user only downloads and updates the submodel relevant to its local data. The process of downloading and updating the required submodel while guaranteeing privacy of the submodel index and the values of updates is known as PRUW. In this work, we study how the communication cost of PRUW can be reduced when a pre-determined amount of distortion is allowed in the reading (download) and writing (upload) phases. We characterize the rate distortion tradeoff in PRUW along with a scheme that achieves the lowest communication cost while working under a given distortion budget.
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。