Federal model training method and device, storage medium and electronic equipment

A training method and model technology, applied in the field of machine learning, can solve the problem of low model training efficiency, achieve the effect of improving accuracy and improving training efficiency

Pending Publication Date: 2022-07-05
YIDU CLOUD (BEIJING) TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present disclosure is to provide a federated model training method, a federated model training device, a computer-readable storage medium, and an electronic device, thereby at least to a certain extent overcoming the model training efficiency caused by limitations and defects of related technologies lower question

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
  • Federal model training method and device, storage medium and electronic equipment
  • Federal model training method and device, storage medium and electronic equipment
  • Federal model training method and device, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known solutions have not been...

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 relates to a federal model training method and device, a storage medium and electronic equipment, and relates to the technical field of machine learning, and the method comprises the steps: carrying out the initialization of a to-be-trained federal model disposed at a server side, obtaining a first model parameter, and transmitting the first model parameter to terminal equipment; receiving a second original model parameter sent by the terminal equipment, and calculating a first quasi-Newton matrix according to the second original model parameter; based on the first quasi-Newton matrix, optimizing a first model parameter included in a to-be-trained federal model arranged at the server side to obtain a third model parameter; and sending the third model parameter to the terminal device, so that the terminal device updates a second original model parameter included in a to-be-trained federal model set by the terminal device according to the third model parameter, and obtaining a trained federal model. According to the invention, the training efficiency of the federal model is improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of machine learning, and in particular, to a federated model training method, a federated model training apparatus, a computer-readable storage medium, and an electronic device. Background technique [0002] Federated learning can complete the training of machine learning models based on decentralized data storage under the premise of protecting user privacy. [0003] In the training task of the existing federated model, the client needs to send the local model to the server; then the server performs model aggregation according to the received models of all clients, and finally sends the aggregated model to the client; Then, by repeating the above process until the model converges or the maximum number of iterations is reached. [0004] However, due to the large amount of data in the federated model itself, there is a high communication load between the server and the client, resultin...

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): G06N20/00G06F17/16
CPCG06N20/00G06F17/16
Inventor马鑫包仁义蒋锦鹏徐松
OwnerYIDU CLOUD (BEIJING) TECH CO LTD