… Because our goal is to evaluate to minimize the time cost of federated learning, rather than
to achieve the best accuracy on this task, we set target accuracy rates of 85%, 88%, and 90%, …

… In summary, compared with centralized learning or distributed learning, federated learning …
usages of federated learning in terms of different optimization objectives of network functions, …

… devices and to facilitate collaborative machine learning of complex models among distributed
devices, a decentralized ML approach called Federated Learning (FL) is introduced in [21]…

… Finally, we build a collaborative federated learning architecture for anomaly traffic detection
in SAGIN to improve communication efficiency. The main contributions are as follows, …

… We propose a federation learning (FL) based algorithm to solve the embedding problem of
SFCs in SAGIN. The algorithm considers different characteristics of nodes and resource load …

… To address these issues, we propose to leverage the popular federated learning to train a …
Accordingly, we can integrate the standard synchronous federated learning (eg, the canonical …

… scalability of modern IoT networks and growing data privacy concerns. Federated Learning
(FL) … of the emerging applications of FL in IoT networks, beginning from an introduction to the …

… These issues can be addressed using Federated Learning (FL) and blockchain. FL can be
used to address the issues of privacy preservation and handling big data generated in STI …

… , we propose a framework called air-ground integrated federated learning (AGIFL), which
organically integrates air-ground integrated networks and federated learning (FL). In AGIFL, …

… research directions of federated learning. Finally, we summarize the characteristics of
existing federated learning, and analyze the current practical application of federated learning. …