… We focus on the personalized federated classification task. Suppose there exist C clients. …
groups of works: personalized federated learning and federated uncertainty quantification. …

… federated learning with Gaussian processes Now we describe our approach for applying
personalized federated learning … how to use Gibbs sampling to learn the NN parameters. Then, …

… federated learning (SFL) that aims to leverage the relation graph among clients to enhance
personalized FL. … optimization framework to include both personalized FL and graph-based …

… In the context of personalized federated learning (FL), the … ActPerFL, a self-aware personalized
FL method where each client … achieve superior personalization performance compared …

… This section explores various model architectures commonly utilized in Personalized
Federated Learning (PFL). We categorize the previous research as shown in Fig. 2, covering key …

… personalized Federated Learning (FL). We propose general optimizers that can be applied
to numerous existing personalized … By examining a general personalized objective capable …

… context of Federated Learning, the accuracy of the global model after personalization should
… between the fields of Federated Learning and Model Agnostic Meta Learning, and raises …

… Concretely, we propose a novel federated learning framework … On the other hand, we formulate
the personalized predictor as … framework which we name Federated Robust Decoupling (…

… Federated learning (FL) is a distributed machine learning paradigm which allows for model
training on decentralized data residing on devices without breaching data privacy. Hence, FL …

… in federated learning also requires a careful design. To address the above challenges, we
propose a novel Hierarchical Personalized Federated Learning … -grained personalized update …