Federated Learning (FL) was originally proposed to effectively exploit more data that are
distributed at local clients even though the local data follow non-iid distributions. The …

Federated learning is a distributed machine learning paradigm where multiple data owners
(clients) collaboratively train one machine learning model while keeping data on their own …

Federated Learning (FL) models often experience client drift caused by heterogeneous data,
where the distribution of data differs across clients. To address this issue, advanced …

Personalized federated learning considers learning models unique to each client in a
heterogeneous network. The resulting client-specific models have been purported to …

Federated learning has emerged as a promising distributed machine learning paradigm to
preserve data privacy. One of the fundamental challenges of federated learning is that data …

Knowledge sharing and model personalization are essential components to tackle the non-
IID challenge in federated learning (FL). Most existing FL methods focus on two extremes: 1) …

Federated Learning (FL) has emerged as a promising solution to perform deep learning on
different data owners without exchanging raw data. However, non-IID data has been a key …

When workers are heterogeneous in computing and transmission capabilities, the global
efficiency of federated learning suffers from the straggler issue, ie, the slowest worker drags …

Data heterogeneity across clients is a key challenge in federated learning. Prior works
address this by either aligning client and server models or using control variates to correct …

Recently, various personalized federated learning (FL) algorithms have been proposed to
tackle data heterogeneity. To mitigate device heterogeneity, a common approach is to use …