Knowledge Distillation in Federated Edge Learning: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Zhiyuan, Sun, Sheng, Wang, Yuwei, Liu, Min, Jiang, Xuefeng, Li, Runhan, Gao, Bo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917604683153408
author Wu, Zhiyuan
Sun, Sheng
Wang, Yuwei
Liu, Min
Jiang, Xuefeng
Li, Runhan
Gao, Bo
author_facet Wu, Zhiyuan
Sun, Sheng
Wang, Yuwei
Liu, Min
Jiang, Xuefeng
Li, Runhan
Gao, Bo
contents 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 technique to tackle the above challenges in FEL. In this paper, we investigate the works that KD applies to FEL, discuss the limitations and open problems of existing KD-based FEL approaches, and provide guidance for their real deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2301_05849
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Knowledge Distillation in Federated Edge Learning: A Survey
Wu, Zhiyuan
Sun, Sheng
Wang, Yuwei
Liu, Min
Jiang, Xuefeng
Li, Runhan
Gao, Bo
Machine Learning
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 technique to tackle the above challenges in FEL. In this paper, we investigate the works that KD applies to FEL, discuss the limitations and open problems of existing KD-based FEL approaches, and provide guidance for their real deployment.
title Knowledge Distillation in Federated Edge Learning: A Survey
topic Machine Learning
url https://arxiv.org/abs/2301.05849