Method and device for checking model feature saliency based on multi-party secure calculation

Abstract

The embodiments of the present specification provide a method and apparatus for checking the feature significance of a linear regression model based on multi-party security calculation. The method is executed by the device of the first data holder among the multiple data holders. The respective devices of each party collectively store N samples and model parameters of the model, and the method includes: jointly performing matrix addition and matrix multiplication based on secret sharing with devices of other data holders, and obtaining the N samples The squared error sum of the samples; jointly perform matrix addition and / or matrix multiplication based on secret sharing with other data holder devices to obtain the value of the jth item on the diagonal of the first matrix; the calculation corresponds to the jth t-test value The second value of ; performs the matrix addition based on secret sharing in conjunction with the equipment of other data holders, and obtains the jth t-test value, so as to determine the corresponding value of the linear regression model based on the jth t-test value salience of features.

Description

technical field [0001] The embodiment of this specification relates to the field of machine learning technology, and more specifically, relates to a method and device for checking feature significance of a linear regression model based on multi-party secure calculation. Background technique [0002] The data needed for machine learning often involves multiple platforms and fields. For example, in the merchant classification analysis scenario based on machine learning, the electronic payment platform has the transaction flow data of the merchants, the e-commerce platform stores the sales data of the merchants, and the banking institution has the loan data of the merchants. Data often exists in silos. Due to issues such as industry competition, data security, and user privacy, data integration is facing great resistance. How to integrate data scattered across various platforms under the premise of ensuring that data is not leaked has become a challenge. [0003] In a linear ...

AI Technical Summary

Problems solved by technology

Due to issues such as industry competition, data security, and user privacy, data integration faces great resistance. How to integrate data scattered across various platforms without data leakage has become a challenge

Images