A model training method and system based on federated learning

A model training and federation technology, applied in the information field, can solve the problem of difficult trade-off between accuracy and privacy, and achieve the effect of ensuring accuracy and data privacy.

Active Publication Date: 2021-04-06
深圳索信达数据技术有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing federated learning method is difficult to balance the accuracy and privacy, the present invention provides a model training method and system based on federated learning

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
  • A model training method and system based on federated learning
  • A model training method and system based on federated learning
  • A model training method and system based on federated learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to better understand the above-mentioned technical solution, the above-mentioned technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0047] refer to figure 1 , in some embodiments, a model training method based on federated learning is provided, the node device and the central server are respectively deployed with a neural network model, the method includes:

[0048] The following steps are iteratively performed until the training stop condition is met:

[0049] S1. The central server sends the parameters to each node device;

[0050] S2. Each node device performs neural network model training based on the parameters and the local data set, and obtains a gradient value;

[0051] S3. Each node device adds noise to its own gradient value, obtains the noise-added gradient value and sends it to the central server, and the central server calculates the sum of the noise-added grad...

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 model training method and system based on federated learning. The method includes: a central server sends parameters to each node device; each node device performs neural network model training based on the parameters and a local data set, and obtains a gradient value; Each node device adds noise to their respective gradient values, obtains the noised gradient value and sends it to the central server, and the central server calculates the sum of the noised gradient values; Sent to the central server; the central server calculates and obtains the sum of gradient values ​​according to the sum of the noise-added gradient values ​​and the sum of the noise values, and obtains updated parameters based on the sum of the gradient values ​​and updates its own neural network model. The parameters are distributed to each node device; this method can ensure the model training accuracy while protecting the private data of the participants.

Description

technical field [0001] The present application relates to the field of information technology, in particular to a model training method and system based on federated learning. Background technique [0002] Federated learning is dedicated to solving the problem of multi-user collaborative model training without disclosing their respective data sets. For example, in the medical big data modeling scenario, each hospital has different patient sample data. Due to the limited amount of data owned by each hospital, if the model is trained only based on its own data, the effect of the model is difficult to meet expectations due to the limitation of the sample size. If the data of various companies can be aggregated for training, the accuracy of the model can be greatly improved. However, due to the competition among hospitals and the requirements for the privacy protection of patient data, it is impossible for hospitals to release their own customer data to any third party, and it...

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 Patents(China)
IPC IPC(8): H04L29/06G06N3/08G06N20/20
CPCG06N3/08G06N20/20H04L63/0407H04L63/0428
Inventor 邵俊何悦路林林
Owner 深圳索信达数据技术有限公司
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