Inherent-attribute-aware dual-graph autoencoder for rating prediction

作     者：Yangtao Zhou Qingshan Li Hua Chu Jianan Li Lejia Yang Biaobiao Wei Luqiao Wang Wanqiang Yang 

作者机构：School of Computer Science and TechnologyXidian UniversityXi'an 710071China Intelligent Financial Software Engineering New Technology Joint LaboratoryXidian UniversityXi'an 710071China Shanghai Fairyland Software Corp.Ltd.Shanghai 200233China 

出 版 物：《Journal of Information and Intelligence》 (信息与智能学报（英文）)

年 卷 期：2024年第2卷第1期

页      面：82-97页

学科分类：080902[工学-电路与系统] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：supported in part by National Natural Science Foundation of China(U21B2015,61972300) in part by Young Scientists Fund of the National Natural Science Foundation of China(62202356) in part by Young Talent Fund of Association for Science and Technology in Shaanxi(20220113) in part by Intelligent Financial Software Engineering New Technology Joint Laboratory Project(99901220858) 

主　　题：Rating prediction Graph convolutional network Autoencoder Inherent attribute aware 

摘      要：Autoencoder-based rating prediction methods with external attributes have received wide attention due to their ability to accurately capture users ***,existing methods still have two significant limitations:i)External attributes are often unavailable in the real world due to privacy issues,leading to low quality of representations;and ii)existing methods lack considering complex associations in users rating behaviors during the encoding *** meet these challenges,this paper innovatively proposes an inherent-attribute-aware dual-graph autoencoder,named IADGAE,for rating *** address the low quality of representations due to the unavailability of external attributes,we propose an inherent attribute perception module that mines inductive user active patterns and item popularity patterns from users rating behaviors to strengthen user and item *** exploit the complex associations hidden in users’rating behaviors,we design an encoder on the item-item co-occurrence graph to capture the co-occurrence frequency features among ***,we propose a dual-graph feature encoder framework to simultaneously encode and fuse the high-order representations learned from the user-item rating graph and item-item co-occurrence *** experiments on three real datasets demonstrate that IADGAE is effective and outperforms existing rating prediction methods,which achieves a significant improvement of 4.51%~41.63%in the RMSE metric.