Federated Transfer Learning with Differential Privacy

arXiv:2403.11343v1 Announce Type: cross
Abstract: Federated learning is gaining increasing popularity, with data heterogeneity and privacy being two prominent challenges. In this paper, we address both issues within a federated transfer learning framework, aiming to enhance learning on a target data set by leveraging information from multiple heterogeneous source data sets while adhering to privacy constraints. We rigorously formulate the notion of \textit{federated differential privacy}, which offers privacy guarantees for each data set without assuming a trusted central server. Under …

address arxiv challenges cs.cr cs.lg data data sets differential privacy federated federated learning framework information math.st privacy source data stat.me stat.ml stat.th target transfer