Federated learning method and system based on state machine, client and electronic equipment

Abstract

The embodiment of the invention provides a federated learning method and system based on a state machine, a client and electronic equipment. After member objects of a target federation learning task created by the server are added into the target federation learning task, the states of the member objects are set as annotation states so as to annotate sample data belonging to private information, and classification labels of the sample data are obtained. And after the member objects in the labeling state are labeled, the states of the member objects are set to be ready states so as to receive and respond to a training instruction which is sent by the server and is used for starting the target federated learning task. And when the server monitors not less than a preset number of member objects in the ready state, a training instruction is sent to the member objects in the ready state. And after receiving the training instruction, the member object in the ready state sets the member object state as an execution state, so as to execute the training operation of the target federated learning task based on the sample data and the corresponding classification label according to a secure multi-party computing protocol.

Description

technical field [0001] This document relates to the field of artificial intelligence technology, in particular to a state machine-based federated learning method, system, client and electronic equipment. Background technique [0002] The deep learning model has been valued by more and more institutions by virtue of its mechanized predictive and identification capabilities. Federated learning can realize joint modeling between institutions on the basis of protecting the privacy of private data of institutions, so as to solve the problem of sample data fragmentation. [0003] At present, federated learning is an emerging technology, and the threshold for its implementation is relatively high. How to invest in low cost and operate efficiently is a technical problem that needs to be solved urgently. Contents of the invention [0004] The purpose of this document is to provide a state machine-based federated learning method, system, client, and electronic equipment, which ...

AI Technical Summary

Problems solved by technology

[0003] At present, federated learning is an emerging technology, and the threshold for realization is relatively high. How to invest in low cost and operate efficiently is a technical problem that needs to be solved urgently.

Images