A Review and Experimental Evaluation on Split Learning

Zhanyi Hu

doi:10.3390/fi17020087

2025-02-13

DOI：10.3390/fi17020087

原文链接

原文求助

摘要

En 中文

在去中心化边缘设备上协同训练深度学习模型最近受到了广泛关注。针对该问题的两种最突出的方案是联邦学习（FL）和分割学习（SL）。尽管已有文献对FL进行了多项综述和实验评估，但SL范式尚未得到系统性的回顾和评估。由于SL范式在标签共享、模型聚合、切层选择等方面存在多样性，缺乏系统性综述使得难以公平且方便地比较不同SL范式的性能。为解决上述问题，本文首先对现有的SL范式进行了全面回顾。然后，我们实现了几种典型的SL范式，并在四个广泛使用的数据集的不同场景下进行了广泛的实验，以比较它们的性能。实验结果为SL范式提供了广泛的工程建议和研究见解。我们希望，通过建立一个公平且易于访问的SL性能评估基准，本研究能够促进未来对SL的研究。

Keyword:

split learning

deep learning

edge computing

期刊

Future Internet

IF:

3.6

论文数:

1.3K

被引数:

6.5K

机构

tencent ai lab

学者数:

论文数: 22

被引数: 1

引用论文

Privacy-Aware Split Learning Based Energy Theft Detection for Smart Grids

Lecture Notes in Computer Science

IF0

2022-08-24

PREAI

Arwa Alromih; John A. Clark; Prosanta Gope

Federated or Split? A Performance and Privacy Analysis of Hybrid Split and Federated Learning Architectures

2021 IEEE 14th International Conference on Cloud Computing (CLOUD)

IF0

2021-09-01

PREAI

Valeria Turina; Zongshun Zhang; Flavio Esposito; Ibrahim Matta

End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things

2020 International Symposium on Reliable Distributed Systems (SRDS)

IF0

2020-09-01

OAAI

Yansong Gao; Minki Kim; Sharif Abuadbba; Yeonjae Kim; Chandra Thapa; Kyuyeon Kim; Seyit A. Camtep; Hyoungshick Kim; Surya Nepal

Mix2SFL: Two-Way Mixup for Scalable, Accurate, and Communication-Efficient Split Federated Learning Mix2SFL: 双向Mixup，可实现可扩展、准确和通信高效的分体式联邦学习

IEEE TRANSACTIONS ON BIG DATA

IF5.7

2024-06-01

OAAI

Oh, Seungeun; Nam, Hyelin; Park, Jihong; Vepakomma, Praneeth; Raskar, Ramesh; Bennis, Mehdi; Kim, Seong-Lyun

The CORA dataset: validation and diagnostics of in-situ ocean temperature and salinity measurements

OCEAN SCIENCE

IF3.3

2013-01-10

176

OAAI

Cabanes, C.; Grouazel, A.; von Schuckmann, K.; Hamon, M.; Turpin, V.; Coatanoan, C.; Paris, F.; Guinehut, S.; Boone, C.; Ferry, N.; Montegut, C. de Boyer; Carval, T.; Reverdin, G.; Pouliquen, S.; Le Traon, P. -Y.

Speed Up Federated Learning in Heterogeneous Environments: A Dynamic Tiering Approach

IEEE INTERNET OF THINGS JOURNAL

IF8.9

2025-03-01

PREAI

Mahmoud Sajjadi Mohammadabadi, Seyed; Zawad, Syed; Yan, Feng; Yang, Lei

Multiple Classification with Split Learning

The 9th International Conference on Smart Media and Applications

IF0

2021-11-04

OAAI

Jongwon Kim; Sungho Shin; Yeonguk Yu; Junseok Lee; Kyoobin Lee