Model training method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a model training method and device, electronic equipment and a storage medium. The scheme is as follows: the server determines a plurality of training devices,sends a training instruction to a plurality of training devices, wherein the training instruction comprises a first model parameter; a second model parameter sent by each piece of training equipmentis received, wherein the second model parameter is obtained by training preset model by training device based on training instruction and training data, the training data is determined according to user data in the training equipment; obtaining a third model parameter by utilizing a joint average algorithm according to a plurality of received second model parameters, judging whether a preset modelcomprising the third model parameter is converged or not, and if yes, determining the third model parameter as the model parameter after training of the preset model is completed. Through the technical scheme provided by the embodiment of the invention, the risk of user privacy disclosure is reduced.

Description

technical field [0001] The present invention relates to the field of computer application technology, in particular to a model training method, device, electronic equipment and storage medium. Background technique [0002] In the process of machine learning, a large number of data sets and labeled data are collected from different user devices as training data, and the training data is sent to the server. The server trains and tests the model according to the received training data to obtain a trained model. [0003] In the above machine learning process, since the collected training data involves a large amount of user privacy, when the training data is sent to the server, and when the server trains the model based on the received training data, the training data may be leaked. risk, leading to the risk of user privacy leakage. Contents of the invention [0004] The purpose of the embodiments of the present invention is to provide a model training method, device, electr...

AI Technical Summary

Problems solved by technology

[0003] In the above machine learning process, since the collected training data involves a large amount of user privacy, when the training data is sent to the server, and when the server trains the model based on the received training data, the training data may be leaked. risk, leading to the risk of user privacy leakage

Images