Differential privacy recommendation method based on heterogeneous information network embedding

Abstract

The invention realizes a set of differential privacy recommendation method based on heterogeneous information network embedding. The differential privacy recommendation method comprises the followingfour steps of: performing network representation learning by using HAN, and calculating heterogeneous attention sensitivity by using characterizations of HAN and an attention weight result; based on adifferential privacy definition, using the heterogeneous attention sensitivity to generate corresponding random noise, and generating a random noise matrix through using a heterogeneous attention random disturbance mechanism; constructing an objective function of differential privacy recommendation embedded with heterogeneous information for learning to obtain a prediction score matrix; and outputting the score matrix as a prediction score capable of keeping privacy. Therefore, the original scoring data is protected for the recommendation system scene under the heterogeneous information network, an attacker is prevented from improving the reasoning attack capability by utilizing the heterogeneous information network data acquired by other channels, and the original scoring data can be guessed or learned again with high probability by observing the recommendation result change of the score.

Description

technical field [0001] The invention relates to the field of recommendation system and privacy protection, in particular to a differential privacy recommendation method based on heterogeneous information network embedding. Background technique [0002] Heterogeneous Information Network (Heterogeneous Information Network) has been widely used in processing heterogeneous network data. It can teach good fusion of heterogeneous network or graph data, and at the same time has better performance and performance in downstream tasks. It is widely used In the task of recommending friends, products, etc. In the work of recommendation system based on collaborative filtering method, heterogeneous information network can integrate different types of nodes and different semantic relations, which has attracted more and more attention. In the real world, the application scenarios of the recommendation system usually contain extensive, diverse and complex network structure information, and ...

AI Technical Summary

Problems solved by technology

In addition to bringing better recommendation results, these rich associated information will also unscrupulously destroy the ability of traditional privacy protection

Images