Federated learning for maximum differential choice based on the global perspective

Boyuan Li; Shengbo Chen; Zihao Peng; Depeng Guo

doi:10.1117/12.2655835

22 December 2022 Federated learning for maximum differential choice based on the global perspective

Boyuan Li, Shengbo Chen, Zihao Peng, Depeng Guo

Proceedings Volume 12508, International Symposium on Artificial Intelligence and Robotics 2022; 1250806 (2022) https://doi.org/10.1117/12.2655835
Event: Seventh International Symposium on Artificial Intelligence and Robotics 2022, 2022, Shanghai, China

Abstract

Federated learning has received extensive attention as a new distributed learning framework, which enables joint modeling without data sharing. However, it is still affected by the communication bottleneck, and most clients may not be able to participate in the joint learning modeling at the same time, resulting in slow convergence. To solve the above problems, we propose a federated learning aggregation algorithm based on a global perspective, which considers the data distribution of participating clients. The server builds a feature distribution table according to the data distribution, and each time the server selects a set of clients for training, it will cover more features to a greater extent to learn the global data more fully. Specifically, the selection of these clients is not random. When the server selects, it will construct a set of clients with the largest mutual distribution difference within the range of visible clients, and place it at the end of the selected chain after each training until all clients’ end is selected. We demonstrate the effectiveness of our work through comprehensive experiments and comparisons between the two most popular algorithms. Specifically, our algorithm achieves an average speedup of 40% compared to traditional algorithms.

Citation Download Citation

Boyuan Li, Shengbo Chen, Zihao Peng, and Depeng Guo "Federated learning for maximum differential choice based on the global perspective", Proc. SPIE 12508, International Symposium on Artificial Intelligence and Robotics 2022, 1250806 (22 December 2022); https://doi.org/10.1117/12.2655835

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Machine learning

Data communications

Data analysis

Data fusion

Neural networks

RELATED CONTENT

Decision support using SAR and LiDAR machine learning target classification...
Proceedings of SPIE (May 27 2022)

Analysis of heterogeneous data model based on federated learning
Proceedings of SPIE (March 28 2023)

Power consumption prediction model and method based on federated learning
Proceedings of SPIE (May 25 2023)

Multi-feature house price trend prediction based on machine learning
Proceedings of SPIE (January 12 2023)

Machine learning how to get more out of HEP...
Proceedings of SPIE (September 11 2015)

Model poisoning attacks against distributed machine learning systems
Proceedings of SPIE (May 10 2019)

Non invasive estimation of intracranial pressure by fast diffuse correlation...
Proceedings of SPIE (January 01 1900)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years