Federated learning system optimization method, device and equipment and storage medium

Abstract

The invention discloses a federated learning system optimization method, apparatus and device, and a storage medium. The method comprises the steps of participating in federated learning model training to obtain a federated model; a preset training data set and the federated model are adopted for training to obtain a local model and a full model, the full model at least comprises the federated model, the local model and a fusion model, and the output of the federated model and the output of the local model are connected with the input of the fusion model; and performing performance test on thefederated model, the local model and the full model, and selecting a finally used model based on a performance test result. According to the method, the federated model is fully utilized, local calculation resources of the participating equipment are not wasted, and the performance of the obtained full model is much better than that of the local model due to the combination of the federated modeland the local model, so that most participating equipment can benefit from federated learning, and the performance of the model is improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a federated learning system optimization method, device, equipment and storage medium. Background technique [0002] At present, in order to protect the data privacy security of the participants of the joint training model, the concept of federated learning is proposed. Federated learning refers to the method of combining different participants for machine learning or deep learning to build a shared machine learning model. In federated learning, participants do not need to expose their own data to other participants and coordinators, so federated learning can well protect user privacy and ensure data security. [0003] However, in the actual application of federated learning, the distribution of data characteristics of the training data owned by different participants is generally different. For example, one participant A may often use the sentence "I have dinn...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a federated learning system optimization method, device, equipment and storage medium, aiming to solve the problem that when the performance of the local model obtained by the participant's local training is better than that of the federated model, the participant chooses to use the local model and abandons the federated model. model, will cause waste of resources, thereby reducing the technical problem of the participant's local computing resource utilization

Images