Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application. (arXiv:2301.04829v1 [cs.LG])

Federated learning (FL) shines through in the internet of things (IoT) with
its ability to realize collaborative learning and improve learning efficiency
by sharing client model parameters trained on local data. Although FL has been
successfully applied to various domains, including driver monitoring
application (DMA) on the internet of vehicles (IoV), its usages still face some
open issues, such as data and system heterogeneity, large-scale parallelism
communication resources, malicious attacks, and data poisoning. This paper
proposes a federated transfer-ordered-personalized learning …

application attacks client communication data dma domains driver efficiency federated learning internet internet of things iot large local malicious monitoring resources scale sharing system things vehicles