Federated learning training method based on model dispersion

Abstract

The invention discloses a federated learning training method based on model dispersion. The invention relates to the field of artificial intelligence in edge calculation. According to the invention, in a real environment, data are often non-uniform and are distributed in a non-independent same manner, and unbalanced distribution of the data enables model updating uploaded to a central server by each client to have different degrees of difference, so that a high-quality model is difficult to train by randomly selecting the clients to participate in training. Meanwhile, the unbalanced distribution of the data can also amplify the influence caused by over-fitting, and model divergence is caused when the influence is serious. According to the method, in order to train a high-quality model under the condition of data imbalance, an updating strategy of a dynamic loss function is adopted to improve the stability of the model, and a client is selected according to the importance of the model,so that the accuracy and convergence rate of the model are improved. Meanwhile, on the basis of the two, a large number of traversal times and a proper regularization parameter mu are selected, so that the performance of the model is optimal.

Description

technical field [0001] The present invention relates to the field of artificial intelligence in edge computing, in particular to a federated learning method based on model dispersion, in particular to a federated learning training method based on model dispersion in the edge environment of the Internet of Things. Background technique [0002] With the advent of the Internet of Things and the era of big data, a large number of smart devices such as sensors are widely used in daily life. These devices are at the edge of wireless networks and are the main way for machine learning and deep learning to obtain training data. The rapid development of artificial intelligence technology in recent years has benefited from the use of these rich data for training. However, with the rapid growth of data volume, the disadvantages of traditional machine learning algorithms become more and more obvious. It uploads all the collected data to the server for training, and the hardware of the e...

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the present invention provides a federated learning training method based on model dispersion, which aims to solve the problem of obvious decline in federated learning performance under the condition of data imbalance

Images