核心概念
FedSOL proposes a novel method in Federated Learning to balance conflicting objectives by adopting an orthogonal learning strategy.
統計資料
Federated learning is an emerging distributed learning framework that preserves data privacy while leveraging client data for training.
FL eliminates the need for direct access to clients' raw data, enabling the use of extensive data collected from various sources.
FedSOL consistently achieves state-of-the-art performance across various scenarios.
引述
"FedSOL is designed to identify gradients of local objectives that are inherently orthogonal to directions affecting the proximal objective."
"Our experiments demonstrate that FedSOL consistently achieves state-of-the-art performance across various scenarios."