In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge
distillation (KD) driven training framework for FL is proposed, where each user can select its …

Federated learning (FL) is a promising distributed learning paradigm in which multiple edge
devices (EDs) collaborate to train a shared model without exchanging privacy-sensitive raw …

Federated learning (FL) supports distributed training of a global machine learning model
across multiple Internet of Things (IoT) devices with the help of a central server. However …

Federated learning (FL) enables distributed clients to collaboratively learn a shared model
while keeping their raw data private. To mitigate the system heterogeneity issues of FL and …

Abstract Knowledge distillation has caught a lot of attention in Federated Learning (FL)
recently. It has the advantage for FL to train on heterogeneous clients which have different …

Federated Learning (FL) has been proposed as a decentralized machine learning system
where multiple clients jointly train the model without sharing private data. In FL, the statistical …

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global
server iteratively averages the model parameters of local users without accessing their data …

Federated learning, as one enabling technology of edge intelligence, has gained substantial
attention due to its efficacy in training deep learning models without data privacy and …

Federated learning (FL) is an emerging learning paradigm without violating users' privacy.
However, large model size and frequent model aggregation cause serious communication …

The heterogeneity of data distributions among clients (non-IID) has been identified as one of
the key challenges in federated learning. In the local training phase, each client model …