Knowledge Distillation in Federated Edge Learning: A Survey

arXiv:2301.05849v3 Announce Type: replace
Abstract: The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine Learning (ML) models without sharing their private data. Limited by device hardware, diverse user behaviors and network infrastructure, the algorithm design of FEL faces challenges related to resources, personalization and network environments. Fortunately, Knowledge Distillation (KD) has been leveraged as an important …

abstract application arxiv cs.lg data demand devices distillation diverse edge hardware intelligent internet internet of things iot knowledge machine machine learning mobile privacy private data protection services survey train type