Robust Decentralized Learning with Local Updates and Gradient Tracking
As distributed learning applications such as Federated Learning, the Internet of Things (IoT),
and Edge Computing grow, it is critical to address the shortcomings of such technologies …
and Edge Computing grow, it is critical to address the shortcomings of such technologies …
[PDF][PDF] Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
Federated Learning (FL) trains a black-box and highdimensional model among different
clients by exchanging parameters instead of direct data sharing, which mitigates the privacy …
clients by exchanging parameters instead of direct data sharing, which mitigates the privacy …
Fast Decentralized Gradient Tracking for Federated Minimax Optimization with Local Updates
CJ Li - arXiv preprint arXiv:2405.04566, 2024 - arxiv.org
Federated learning (FL) for minimax optimization has emerged as a powerful paradigm for
training models across distributed nodes/clients while preserving data privacy and model …
training models across distributed nodes/clients while preserving data privacy and model …