Federated learning model training method based on data feature perception aggregation

A technology of data characteristics and learning models, applied in computing models, machine learning, electrical digital data processing, etc., can solve the problems of magnified statistical heterogeneity and model effects that cannot meet the requirements, so as to alleviate the impact, avoid communication, and improve The effect of model training efficiency

Pending Publication Date: 2021-03-12
HANGZHOU DIANZI UNIV
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Using the federated learning method in the edge computing scenario will amplify the existing statistical heterogeneity. When the statistical heterogeneity is large enough, the trained model effect will not meet the required effect.

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
  • Federated learning model training method based on data feature perception aggregation
  • Federated learning model training method based on data feature perception aggregation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention can be more fully understood from the following description taken in conjunction with the accompanying drawings. Other additional aspects of the invention, such as the features and / or advantages of the exemplary embodiments, will be apparent from the description below, or learned by practice of specific embodiments in accordance with the teachings of the invention.

[0019] Such as figure 1 As shown, the system model of the present invention consists of two entities: an edge client and a cloud server. These are described as follows:

[0020] (1) Edge client: the user's terminal device has certain data calculation and storage functions. In order to solve the problem of privacy leakage, the edge client first independently performs protection processing on local data and local models to meet differential privacy; then only Upload the local model to the cloud server.

[0021] (2) Cloud server: The cloud server stored in a large data center has power...

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 provides a federated learning model training method based on data feature perception aggregation. According to the method, a cloud server calculates a global optimal model according to alocal model uploaded by an edge client, performs dimension reduction on data characteristics according to mined edge client data characteristics, screens out key characteristics, and performs clustering grouping on the edge client based on the key characteristics; the cloud server issues grouping information and a global optimal model to the edge client; and the edge client provides local data according to the received global optimal model and provides local execution model training according to the global optimal model, and one local model is randomly selected from the same edge client groupor the optimal model in the edge client group is selected and uploaded to the cloud server. According to the method, the data characteristics of the edge clients are fully utilized, the edge clientsare grouped, unnecessary communication is avoided, the influence of statistical isomerism on model training is relieved to a great extent, and the training efficiency of the model is improved.

Description

technical field [0001] The invention relates to the field of edge computing, in particular to a federated learning model training method based on data feature perception aggregation. Background technique [0002] Since cloud computing was proposed in 2005, it has gradually changed the way we live, study and work. Services provided by software such as Google and Facebook that are often used in daily life are typical representatives. Moreover, scalable infrastructure and processing engines that can support cloud services have also had a certain impact on our business model, such as Hadoop, Spark, and so on. The rapid development of the Internet of Things has brought us into the post-cloud era. In our daily life, a large amount of data will be generated so that the cloud computing model can no longer solve the current problems well. Therefore, a new computing model has emerged, the edge calculate. Edge computing refers to processing data at the edge of the network, which can...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N20/00G06F9/50G06K9/62
CPCG06N20/00G06F9/5072G06F18/23
Inventor 曾艳赵乃良燕忠毅张纪林袁俊峰任永坚周丽
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap