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

Federated model training method and system and electronic equipment

A technology for model training and training methods, applied in the computer field, which can solve problems such as data quality differences, unavailability, and the inability of federated models to terminate

Inactive Publication Date: 2020-03-10
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of this specification provides a federated model training method, system and electronic equipment, which are used to solve the problem that the federated model cannot be terminated or is unavailable due to the difference in data quality of the client

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 model training method and system and electronic equipment
  • Federated model training method and system and electronic equipment
  • Federated model training method and system and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] In order to make the purpose, technical solution and advantages of this document clearer, the technical solution of this document will be clearly and completely described below in conjunction with specific embodiments of this specification and corresponding drawings. Apparently, the described embodiments are only some of the embodiments in this document, not all of them. Based on the embodiments in this specification, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this document.

[0064] Such as figure 1 As shown, an embodiment of this specification provides a federated model training method 100, which can be jointly executed by a server and multiple clients, and includes the following steps:

[0065] S102: The server generates first adversarial model parameters, and sends the first adversarial model parameters to the client.

[0066] Such as figure 2 as shown, figure 2 Schematica...

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 embodiment of the invention discloses a federated model training method and system and electronic equipment, and the method comprises the steps that a server generates a first adversarial model parameter, and transmits the first adversarial model parameter to a client; the client performs generative adversarial training based on the output generative model and the first adversarial model parameter, and outputs generated data; the client performs federation model training based on the real data and the generated data to obtain a first federation model parameter, and sends the first federation model parameter to the server; and the server integrates the first federation model parameters of the plurality of clients to obtain second federation model parameters.

Description

technical field [0001] This document relates to the field of computer technology, in particular to a federated model training method, system and electronic equipment. Background technique [0002] With the continuous development of artificial intelligence, artificial intelligence plays a pivotal role in industrial applications, but a series of new problems follow, such as the problem of data islands formed by scattered data, and the increasingly concerned Data privacy and data security issues. [0003] Federated learning conducts model training through parameter exchange under an encryption mechanism, which can effectively help multiple clients use multi-party data and jointly model while meeting user privacy protection, data security, and government regulations. [0004] However, in related technologies, the solution to the federated model cannot be terminated or is unavailable often due to differences in data quality of local clients, for example, unbalanced data distri...

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): G06N20/00
CPCG06N20/00
Inventor 刘磊
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com