
The authors propose two novel privacy-preserving federated primal-dual learning algorithms, DP-FedPDM and BSDP-FedPDM, to efficiently solve non-convex and non-smooth federated learning problems while considering communication efficiency and privacy protection.


coremsg

privacy-preserving-federated-primal-dual-learning-for-non-convex-and-non-smooth-problems-with-bidirectional-model-sparsification


Privacy-Preserving Federated Primal-Dual Learning for Non-convex and Non-smooth Problems with Bidirectional Model Sparsification
