Secure Vertical Federated Learning Under Unreliable Connectivity

arXiv:2305.16794v2 Announce Type: replace
Abstract: Most work in privacy-preserving federated learning (FL) has focused on horizontally partitioned datasets where clients hold the same features and train complete client-level models independently. However, individual data points are often scattered across different institutions, known as clients, in vertical FL (VFL) settings. Addressing this category of FL necessitates the exchange of intermediate outputs and gradients among participants, resulting in potential privacy leakage risks and slow convergence rates. Additionally, in many real-world scenarios, VFL training …

arxiv client clients connectivity cs.cr cs.lg data data points datasets features federated federated learning institutions points privacy settings train under work