论文标题
在联邦学习中使用顶级$ r $稀疏的收入私人存储权衡
Rate-Privacy-Storage Tradeoff in Federated Learning with Top $r$ Sparsification
论文作者
论文摘要
我们调查了使用最高$ r $稀疏的联邦学习（FL）中的费率，隐私和存储之间的权衡取舍，在此，FL系统中的用户和服务器仅共享FL过程中最重要的$ r $和$ r'$分数，以降低通信成本。我们提出的方案可以保证用户以较大的存储成本牺牲用户发送的稀疏更新的价值和索引的理论隐私。为此，我们概括了通过允许一定量的信息泄漏来降低存储成本的计划。因此，我们在私人FL的沟通成本，存储成本和信息泄漏之间提供了与两个拟议方案的渠道之间的一般权衡取舍。
We investigate the trade-off between rate, privacy and storage in federated learning (FL) with top $r$ sparsification, where the users and the servers in the FL system only share the most significant $r$ and $r'$ fractions, respectively, of updates and parameters in the FL process, to reduce the communication cost. We present schemes that guarantee information theoretic privacy of the values and indices of the sparse updates sent by the users at the expense of a larger storage cost. To this end, we generalize the scheme to reduce the storage cost by allowing a certain amount of information leakage. Thus, we provide the general trade-off between the communication cost, storage cost, and information leakage in private FL with top $r$ sparsification, along the lines of two proposed schemes.
