Longitudinal federated learning linear regression and logistic regression model training method and device

Abstract

The invention discloses a longitudinal federated learning linear regression and logistic regression model training method and device, computer equipment and a storage medium, and the method comprises the steps: encrypting local training data of each participant through each participant, and exchanging the encrypted ciphertext; obtaining an intersection ciphertext of a sample intersection owned by the participant through an exchangeable encryption mode; randomly selecting data in the plurality of intersection ciphertexts, obtaining an intermediate result ciphertext of the participant according to the selected data, decrypting the intermediate result ciphertext, and calculating an encryption aggregation gradient according to a decryption result; decrypting the encrypted aggregation gradient to obtain a gradient for updating the parameters of the participant model; and updating the model, judging whether an iteration termination condition is met or not, if so, ending iteration, and if not, continuing training. The technical problem that in the prior art, due to data privacy and lack of trust among different organizations, sensitive data of all the organizations are difficult to fully utilize for distributed machine learning model training is solved.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a longitudinal federated learning linear regression and logistic regression model training method, device, computer equipment and storage medium. Background technique [0002] As an emerging technology leading a new generation of industrial transformation, artificial intelligence has been more and more widely used in people's production and life. The development of artificial intelligence is inseparable from the massive data that supports its training models. However, the practical application of artificial intelligence technology in various industries faces many challenges, including privacy, security and efficiency, and its data is an important factor affecting the development of applications. Due to the privacy issues of training data and trust issues among participants, it is difficult to circulate private data among enterprises, that is, the potential app...

AI Technical Summary

Problems solved by technology

[0007] For this reason, this application proposes a vertical federated learning linear regression and logistic regression model training method and device, which solves the problem that the sensitive data of each organization is difficult to fully utilize due to the privacy of data and the lack of trust between different organizations in the prior art Technical Issues for Distributed Machine Learning Model Training

Images