Model training method and device based on federal learning system, and electronic equipment

Abstract

The invention provides a model training method and device based on a federal learning system. The method comprises the following steps: acquiring first model parameters of a first sub-model corresponding to at least two model training labels and second model parameters of a second sub-model corresponding to the at least two model training labels; obtaining a label meaning of each model training label, and determining an association relationship between the at least two model training labels based on the label meaning; performing parameter aggregation on the at least two first model parameters and the second model parameters based on an association relationship between the at least two model training labels to obtain global model parameters; and distributing the global model parameter to each first participant device and the second participant device, so that the first participant device and the second participant device update the model parameter of the local model based on the global model parameter. Through the method and the device, the data security can be ensured, and the prediction accuracy of the model is improved.

Description

technical field [0001] This application relates to the technical field of artificial intelligence, and in particular to a model training method, device, electronic equipment and computer-readable storage medium based on a federated learning system. Background technique [0002] Federated learning technology is an emerging privacy protection technology that can effectively combine data from all parties for model training without leaving the local data. [0003] In related technologies, usually only one label provider and one feature provider are supported to participate in the training of the federated learning model. Since the number of training samples provided by the label provider is relatively small compared with the number of training samples of the entire federated learning model, in related Under the vertical federated learning framework with the participation of an ordinary single label provider, if only the feature provider is used to model, it is easy to lead to ov...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, usually only one label provider and one feature provider are supported to participate in the training of the federated learning model. Since the number of training samples provided by the label provider is relatively small compared with the number of training samples of the entire federated learning model, in related Under the vertical federated learning framework with the participation of an ordinary single label provider, if only the feature provider is used to model, it is easy to lead to overfitting of the resulting model and inaccurate model prediction results. For example, when a local bank decides on a loan amount or a credit card amount, Will result in loan amount being too high or too low

Images