In federated learning (FL), a machine learning (ML) model is collectively trained by a large number of users, using their private data in their local devices. With top $r$ sparsification in FL, the users only upload the most significant $r$ fraction of updates, and the servers only send the most significant $r'$ fraction of parameters to the users in order to reduce the communication cost. However, the values and the indices of the sparse updates leak information about the users' private data. In this work, we consider an FL setting where $N$ non-colluding databases store the model to be trained, from which the users download and update sparse parameters privately, without revealing the values of the updates or their indices to the databases. We propose four schemes with different properties to perform this task while achieving the minimum communication costs, and show that the information theoretic privacy of both values and positions of the sparse updates can be guaranteed. This is achieved at a considerable storage cost, though. To alleviate this, we generalize the schemes in such a way that the storage cost is reduced at the expense of a certain amount of information leakage, using a model segmentation mechanism. In general, we provide the tradeoff between communication cost, storage cost and information leakage in private FL with top $r$ sparsification.
翻译:在联合学习(FL)中,一个机器学习(ML)模式由大量用户集体培训,使用当地设备中的私人数据。在FL中,用户只上传了最重要的一部分更新金额,服务器只向用户发送了最重要的一部分参数,以减少通信成本。然而,少许更新的数值和指数泄露了用户的私人数据。在这项工作中,我们考虑一个FL设置,其中非熔化数据库用美元储存模型,用户私下下载和更新稀有参数,而不向数据库披露更新或索引的价值。我们提出四项具有不同属性的计划,以便在实现最低通信成本的同时执行这项任务,并表明对稀薄更新的价值和位置的信息的理论隐私权可以保证,但这是以相当高的存储成本实现的。为了减轻这一点,我们推广了这种计划,使存储成本降低以一定量的信息泄漏成本,同时使用模型化的存储成本,使用高级存储机制,我们提供了在FSAR(F)交易中以最高存储成本计算的存储成本。</s>