Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Lightweight excitation model training method based on hierarchical federal learning

An incentive model and lightweight technology, applied in computing models, machine learning, computing, etc., can solve the problems of poor HFL training effect and limited number of HFL end-side users, saving training costs and improving training effects.

Pending Publication Date: 2021-06-29
TIANJIN UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, it is found that the number of end-side users of the existing HFL is limited, resulting in poor training effect of HFL, and there is currently no suitable incentive method to encourage end-side users to join in the model training of HFL

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Lightweight excitation model training method based on hierarchical federal learning
  • Lightweight excitation model training method based on hierarchical federal learning
  • Lightweight excitation model training method based on hierarchical federal learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. It should be understood, however, that these descriptions are exemplary only, and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

[0077] The terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting of the present disclosure. The terms "comprising", "comprising", etc. used herein indicate the presence of features, steps,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a lightweight excitation model training method based on hierarchical federated learning, and belongs to the technical field of federated learning. The training method comprises the following steps: determining a target end-side user from end-side users according to initial unit data cost information of the end-side users to generate a target end-side user group; calculating an optimal cloud side strategy of the cloud side server according to the initial unit data cost information of each target end side user; calculating an optimal edge side strategy of each edge aggregator according to the optimal cloud side strategy; calculating an optimal end-side strategy of each target end-side user in a target end-side user group corresponding to the current edge aggregator according to the optimal edge-side strategy of each edge aggregator; and training an excitation model according to the optimal cloud side strategy, the optimal edge side strategy and the optimal end side strategy to obtain a trained excitation model. The invention also discloses a training system, an excitation method and an excitation system of the lightweight excitation model based on hierarchical federal learning.

Description

technical field [0001] The invention belongs to the technical field of federated learning, and in particular relates to a training method and an incentive method for a lightweight incentive model based on hierarchical federated learning. Background technique [0002] Recent developments in deep learning have revolutionized many application domains, such as image processing, natural language processing, video analysis, etc., including the field of electricity. The great success of deep learning in these fields stems from the availability of large amounts of training data and massive computing power. However, for reasons of user data security, computing cost, and efficiency, the concept of end-edge-cloud hierarchical federated learning (HFL) was proposed. [0003] Device-Edge-Cloud Hierarchical Federated Learning (HFL) can effectively reduce communication overhead while still making full use of abundant data on the device side. Although HFL has many advantages, it also has s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06N20/00
CPCG06N20/00
Inventor 王晓飞赵云凤刘志成仇超邓辉刘立群
Owner TIANJIN UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com