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

Abstract

The invention discloses a federal model training method and device, electronic equipment and a storage medium, the method is executed by a server in a federal model training system, and the method comprises the following steps: issuing a global model corresponding to a target task to each edge working node; based on a preset algorithm, determining a specified number of local models participating in global model updating according to the current network resources and the number of the target tasks; and when a specified number of local model update data is received, performing federal aggregation to obtain an updated global model. According to the technical scheme provided by the embodiment of the invention, the number of local models participating in global model training is dynamically determined by combining the preset algorithm with the network resources of each iteration, so that the network resource utilization rate of model training in the federated learning process is effectively improved; the problem that the federated model cannot converge due to the problem that network resources are limited is avoided, and the training performance of the federated model is greatly improved.

Description

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

AI Technical Summary

Benefits of technology

This patented technology allows multiple edges work nodes (also called clients) send their own world-model trained locally from one centralized entity into another without having them share any computing resource or slow down processing speed. It also uses predetermined algorithms instead of constantly updating all models at once during this phase. By doing these techniques, collaborative filtering systems improve efficiency while still maintaining good accuracy when performing complex operations such as image recognition.

Problems solved by technology

This patented describes different ways that collaborative systems use distributed processing techniques such as Federating Learning (FL) may be vulnerable due to their lacking ability to prevent unauthorized access by users during communication sessions between client devices and service providers. To address this issue, researchers have proposed solutions like secure multi-party computation protocols with encrypted versions of shared secret keys called shares on both edges and workers' computers. However these methods require significant amounts of time and resources to perform complex calculations when updating large datasets over multiple machines at once.

Images