Method, system and device for updating model parameters based on federated learning

Abstract

The invention relates to a method, system and device for updating model parameters based on federated learning. The method, system and device can be used for data privacy protection. The method is realized by any training member in participants, and the method comprises the following steps: carrying out multiple rounds of iterative updating on model parameters, wherein one round of iterative updating comprises the following steps: obtaining a to-be-trained model with the same structure as other participants; training the to-be-trained model based on a self-held training sample and a sample label to obtain a gradient matrix; calculating a first operation value matrix at least based on the gradient matrix and a first hyper-parameter; calculating a second operation value matrix based on the gradient matrix; uploading the first operation value matrix and the second operation value matrix to the server, so that the server updates model parameters of a to-be-trained model of a server side; and obtaining updated model parameters from the server so as to take the updated model parameters as a to-be-trained model for the next round of iterative update, or determining a final model based onthe updated model parameters.

Description

technical field [0001] One or more embodiments of this specification relate to multi-party data joint processing, and in particular to a method, system and device for updating model parameters based on federated learning. Background technique [0002] In data analysis, data mining, economic forecasting and other fields, machine learning models can be used to analyze and discover potential data value. Since the data held by a single data owner may be incomplete, it is difficult to accurately describe the target. In order to obtain better model prediction results, the federated learning of the model is carried out through the data cooperation of multiple data owners. has been widely used. In the process of model training using federated learning, it is expected that the data sets held by multiple parties are all of the same distribution. However, in actual situations, the data distribution of the data sets held by all parties is quite different, which makes the model trainin...

AI Technical Summary

Problems solved by technology

However, in actual situations, the data distribution of the data sets held by all parties is quite different, which makes the model training process prone to bias due to the influence of unevenly distributed data when using federated learning for model training. Affect the efficiency of model training

Images