中圖分類號：TP391
文獻(xiàn)標(biāo)識碼：A
DOI:10.19358/j.issn.2097-1788.2023.03.012
引用格式：于曉明，周淦，劉志春.基于用戶特定空間的對抗推薦模型［J］.網(wǎng)絡(luò)安全與數(shù)據(jù)治理，2023,42(3):74-79.

Adversarial recommendation model based on user-specific space

Abstract： Autoencoder and generative adversarial networks, as powerful models, have been applied to the field of recommendation systems to supplement the interactive information between users and items However, under this mode of training, a large amount of auxiliary information is wasted, such as userspecific information This paper combines autoencoder, generative adversarial networks, and auxiliary information to propose an adversarial recommendation model based on userspecific space (USSGAN). In order to establish the connection between auxiliary information and interactive information, the hidden space of the autoencoder is replaced by the userspecific space The pointtopoint mapping of interactive information and userspecific information limits the representation of the model Therefore, the adversarial training is added to the userspecific space to improve the performance of the modelExtensive experiments on two public movie datasets demonstrate the effectiveness and superiority of the proposed model

Key words : generative adversarial networks; userspecific space; autoencoder; recommendation systems