Heterogeneous scene-oriented asynchronous federal learning method and device and storage medium

A learning method and federated technology, applied in the field of artificial intelligence, can solve problems that have not been discussed in depth, and achieve the effect of improving model accuracy and reducing communication costs

Pending Publication Date: 2022-02-11
SUN YAT SEN UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to integrate client activation, communication optimization, and aggregation enhancement strategies to improve mode...

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
  • Heterogeneous scene-oriented asynchronous federal learning method and device and storage medium
  • Heterogeneous scene-oriented asynchronous federal learning method and device and storage medium
  • Heterogeneous scene-oriented asynchronous federal learning method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0051] Aiming at the problems existing in the existing technology, the present invention proposes a three-stage asynchronous federated learning mechanism for heterogeneous scenarios, which realizes the integration of client activation, communication optimization and aggregation enhancement strategies, and reduces communication costs while improving model accuracy , to effectively support asynchronous federated learning, such as figure 1 Shown, method of the present invention comprises the following steps:

[0052] determining a target client from candidate clients, wherei...

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 heterogeneous scene-oriented asynchronous federal learning method and device and a storage medium, and the method comprises the steps of determining a target client from candidate clients, the autocorrelation entropy of the target client being higher than the autocorrelation entropy of other clients in the candidate clients; training the target client to obtain a target parameter, and uploading the target parameter to a server; enabling the server to perform aggregation enhancement processing on a model aggregation process according to the target parameter to obtain a first federated model; performing strategy integration processing on the first federated model to obtain a second federated model; and performing model evaluation on the second federated model to determine a target federated model. The invention can improve the model accuracy and reduce the communication cost, and can be widely applied to the technical field of artificial intelligence.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an asynchronous federated learning method, device and storage medium for heterogeneous scenarios. Background technique [0002] With the rapid development of the Internet of Things, a multifunctional network has been created to connect a large number of devices in various fields such as transportation, health care, and administrative management to support diverse data perception and service experience improvement. However, as user information becomes sensitive, the mode of data being collected uniformly in the data center may violate laws and regulations related to data security and privacy protection, making the data processing paradigm begin to shift from centralized data integration to distributed parameter aggregation. [0003] In order to eliminate data islands caused by data security and data privacy, a decentralized mechanism called federated learni...

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): G06N20/20
CPCG06N20/20
Inventor 由林麟刘晟蔡铭章圣律郭子晗周檬贺俊姝
Owner SUN YAT SEN 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