Privacy-Preserving Federated Singular Value Decomposition

Singular value decomposition (SVD) is a fundamental technique widely used in various applications, such as recommendation systems and principal component analyses. In recent years, the need for privacy-preserving computations has been increasing constantly, which concerns SVD well. Federated emerged promising approach that enables collaborative computation without sharing raw data. However, existing federated approaches still improvements regarding privacy guarantees utility preservation. This paper moves step further towards these directions: we propose two enhanced schemes focusing on privacy, respectively. Using system use-case with real-world data, demonstrate our outperform state-of-the-art solution. Our utility-enhanced scheme (utilizing secure aggregation) improves final convergence speed by more than 2.5 times compared approach. contrast, privacy-enhancing differential privacy) provides robust protection while improving same aspect 25%.