Federal learning-based model parameter updating method, device and equipment

Abstract

The embodiment of the invention provides a federal learning-based model parameter updating method, device and equipment, and the method comprises the steps: receiving a model parameter updating instruction which is issued by a federated learning server and aims at a target graph neural network model, wherein the model parameter updating instruction carries a first sharing parameter, and the target graph neural network model is a common model of a plurality of federated learning clients; based on the first shared parameter, a locally stored first independent parameter and map data constructed by local user private data, training the target map neural network model to obtain a model parameter of the trained target map neural network model; and sending the second sharing parameter to the federated learning server, so that the federated learning server updates the first sharing parameter of the target graph neural network model based on the second sharing parameter sent by a plurality of federated learning clients.

Description

technical field [0001] This document relates to the technical field of data processing, and in particular to a method, device and equipment for updating model parameters based on federated learning. Background technique [0002] With the rapid development of computer technology, the types and quantities of application services provided by enterprises to users are also increasing, and the amount of user data is increasing, and the data structure is becoming more and more complex. Therefore, enterprises often use A graph neural network model built on knowledge graphs to process intricate user data. [0003] After the enterprise builds the graph neural network model, it can update the model parameters of the graph neural network model based on local user data. However, the amount of user private data stored locally by the enterprise is small, the data quality is poor, and in order to protect the privacy of user data Security, data collaboration cannot be realized between diffe...

AI Technical Summary

Problems solved by technology

[0003] After the enterprise builds the graph neural network model, it can update the model parameters of the graph neural network model based on local user data. However, the amount of user private data stored locally by the enterprise is small, the data quality is poor, and in order to protect the privacy of user data Security, data collaboration cannot be realized between different enterprises, or even between different business units in the same enterprise. Therefore, updating the model parameters of the graph neural network model based on local user data will make the update accuracy of the model parameters poor. Therefore, it is necessary to A solution that can improve the update accuracy of model parameters

Images