Data transmission method and device for transverse federation learning, terminal equipment and medium

Abstract

The invention discloses a data transmission method and device for transverse federation learning, terminal equipment and a computer readable storage medium. The method comprises the following steps: receiving a residual pooling model uploaded by each client in transverse federation learning, wherein each client determines a to-be-trained model in transverse federated learning according to an aggregation result received from the server and an initial to-be-trained model, performs local model training on the to-be-trained model by using local training data, calculates a residual error, and performs pooling compression on the residual error to obtain a residual error pooling model; performing preset aggregation operation on the received residual pooling model to obtain an aggregation result;and issuing the aggregation result to each client, so that each client performs a new round of model training according to the aggregation result. According to the invention, the data transmission quantity between the client and the server is reduced, and the problems of complex implementation process and loss of model precision caused by intermediate transmission through model cutting are avoided.

Description

technical field [0001] The present invention relates to the technical field of horizontal federated learning, in particular to a data transmission method, device, terminal device and computer-readable storage medium for horizontal federated learning. Background technique [0002] At present, when the number of clients participating in horizontal federated learning is large, each client uploads data such as model updates at the same time, which will lead to a very heavy operating pressure on the server side of horizontal federated learning, and the model based on machine learning is very complicated. The structure of the model is usually relatively large, which requires each client to establish a communication connection with the server for a long time. In view of the instability of the federated learning communication network environment, the data transmission between each client and the server is easily interrupted. [0003] Currently, in order to reduce the operating press...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a data transmission method, device, terminal equipment and computer-readable storage medium for horizontal federated learning, aiming to solve the existing problem of horizontal federated learning The training model in federated learning is cut and compressed and then transmitted. The implementation process is complicated and will cause technical problems in the loss of training model accuracy.

Images