High-robustness privacy protection recommendation method based on adversarial learning

Abstract

The invention provides a high-robustness privacy protection recommendation method based on adversarial learning. The method comprises the following steps: constructing a training set required for optimizing a neural collaborative filtering model and a reference set required for training a member reasoning model; designing a neural collaborative filtering joint model with member reasoning regular terms, and performing iterative optimization of a confrontation training mode on the joint model by using the training set and the reference set to obtain a robust user and article feature representation matrix; predicting an unobserved score according to the obtained user feature matrix and the article feature matrix; and recommending the corresponding item set which is relatively high in prediction score and does not generate behaviors to the corresponding user. According to the invention, a unified minimum and maximum objective function is designed in an adversarial training mode to explicitly endow the recommendation algorithm with the ability of defending member reasoning attacks, so that the member reasoning attacks can be defended, overfitting of the recommendation model can be relieved, and bidirectional improvement of personalized recommendation model algorithm performance and training data privacy protection is realized.

Description

technical field [0001] The invention relates to the technical field of personalized recommendation, in particular to a highly robust privacy protection recommendation method based on adversarial learning. Background technique [0002] Personalized recommendation system, as an effective supplement to traditional information retrieval, makes full use of the content characteristics of users and items and the interaction data between them to automatically filter useless information. It is a common application that can help users discover their potential interests. It has received increasing attention in both academia and industry. The core technical support behind the personalized recommendation system is a recommendation algorithm that uses machine learning ideas to train users' historical browsing data. [0003] The reason why the recommendation algorithm can grasp the user's future interests and preferences is that it needs to collect as much user personal information and be...

AI Technical Summary

Problems solved by technology

However, because the existing differential privacy mechanism meets the requirements of privacy protection in a strict mathematical sense, and does not explicitly incorporate the model prediction performance into the design goal of the privacy mechanism, it often causes serious loss of prediction accuracy.

Images