Unlock instant, AI-driven research and patent intelligence for your innovation.

Training method of neural network model

A neural network model and training method technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve problems such as inability to protect original user data privacy, user privacy theft, etc. The effect of improving efficiency

Pending Publication Date: 2022-02-01
SHANGHAI UNIVERSITY OF INTERNATIONAL BUSINESS AND ECONOMICS +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a neural network model training method, which solves the problem that the original user data cannot be effectively protected for privacy in the prior art, and the user privacy is prevented from being stolen after the data is leaked

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
  • Training method of neural network model
  • Training method of neural network model
  • Training method of neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0036] The "plurality" mentioned herein means two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and / or B may indicate: A exists alone, A and B exist simultaneously, and B exists independently. The character " / " generally indicates that the contextual objects are an "or" relationship.

[0037] In related technologies, the original user data is subjected to differential privacy processing by a single differential privacy algorithm to obtain disturbed data, but when the collector steals the disturbed data, it can analyze the disturbed data by various means, thereby stealing user privacy . Such as figure 1 As shown, it is as...

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 training method of a neural network model, and belongs to the field of computer networks. The method comprises: acquiring original user data, determining node data in the original user data and a first adjacency matrix, and the first adjacency matrix being used for representing the relation between the node data; performing differential privacy processing on the adjacent matrix based on a Laplacian noise mechanism to obtain a second adjacent matrix; performing differential privacy processing on the first node feature matrix of the node data based on a Gaussian noise mechanism to obtain a second node feature matrix; and constructing a graph convolutional neural network prediction model based on the second adjacency matrix and the second node feature matrix, and performing model training on the graph convolutional neural network prediction model. The disturbance data output by the scheme shows the characteristics of irregularity and high robustness against attacks, and the privacy protection efficiency can be improved.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a training method of a neural network model. Background technique [0002] With the in-depth development of graph neural network theory in social network relations and recommendation systems, people gradually began to pay attention to the privacy protection of node information. With the support of big data, it is very easy to obtain the user's private information through the node information of the user data. [0003] In related technologies, the original user data is perturbed mainly through the algorithm of differential privacy, and the data stealer is confused by adding noise, so that the data stealer cannot tell whether the stolen data contains private information. [0004] However, in the existing technology, since data thieves can infer the sensitive information of the data through noise filtering, big data and machine learning, and statis...

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): G06F21/62G06K9/62G06N3/04G06N3/08
CPCG06F21/6245G06N3/08G06N3/045G06F18/2415
Inventor 刘峰杨成意齐佳音周爱民李志斌
Owner SHANGHAI UNIVERSITY OF INTERNATIONAL BUSINESS AND ECONOMICS