… a novel personalized federated learning framework in a … employs personalized sparse
masks to customize sparse local … , we propose a decentralized sparse training technique, which …

… The goal of traditional federated learning (FL) is to fit a single … , we focus on the personalized
federated learning problem in … thus it is promising to learn personalized model hθi ∈ H : X ↦…

… federated learning with personalized sparse mask (FedSpa), a novel PFL scheme that employs
personalized sparse masks to customize sparse … training (aka sparse-to-sparse training), …

… achieve good sparse personalization, which is better than the personalized methods based
… of this sparse personalization architecture compared with the state-of-the-art personalization …

… personalization when developing federated learning methods. In this work, we propose a
personalized federated learning (… Specifically, we aim to learn the regression weight by solving …

… cal personalized federated learning framework. Our approach includes a personalized
edge … performance and allowing for personalized user models. Furthermore, our hierarchical …

… Federated Learning (FL) is a collaborative machine learning technique to train a … personalized
federated learning via maximizing correlation (pFedMac), and further extend it to sparse …

… faster and greater model sparsity. Although our pruning method is contrary to non-federated
pruning practices, we find that it can be leveraged in federated learning due to the special …

… , we propose a novel federated learning framework and algorithm for learning a shared data
… over alternative personalized federated learning approaches in heterogeneous settings. …

… To improve computation efficiency on device in a hardwarefriendly way, we employ the
structured sparsity regularization during mask optimization to learn binary masks with structured …