计算机科学与探索2024，Vol.18Issue(7)：1792-1805,14.DOI:10.3778/j.issn.1673-9418.2305022
融合多个性化桥和自监督学习的跨域推荐算法
Cross-Domain Recommendation Algorithm Combining Multi-personalized Bridges and Self-supervised Learning
摘要
Abstract
A cross-domain recommendation algorithm combining multi-personalized bridges and self-supervised learning(MS-PTUPCDR)is proposed for users with less project interaction in the target domain in the cross-domain rec-ommendation system.Firstly,a variational bipartite graph encoder is added to the target domain,and a variational in-ference framework is used to generate potential variables.The target domain user representation aggregates their isomor-phic neighbor information.Secondly,the user·s single preference bridge is extended to the user·s multi-personalized preference bridge,the user·s transferable user factors in the multi-source domain are transferred to the target do-main,and the multi-head attention mechanism is added to the target domain to fuse the user·s potential factors from different source domains as the auxiliary task of self-supervised learning.Finally,this paper aggregates user neigh-bor factors and the fused user multi-source domain transfer user factors for self-supervised learning.In the target do-main,the project score of the target domain is predicted by the dot product of the user factor and the project factor of the target domain after the user·s supervised learning.The algorithm is tested on two datasets,Amazon and MovieLens,and the results show that the algorithm outperforms the comparative baseline algorithm in terms of MAE and RMSE evaluation metrics.Compared with the optimal comparative baseline algorithm on both datasets,the MAE is im-proved by 1.96% on average,and the RMSE is improved by 1.92% on average,which verifies the effectiveness of the algorithm.关键词
跨域推荐/用户多个性化偏好桥/多头注意力机制/自监督学习/变分二部图编码器Key words
cross-domain recommendation/multi-personalized preference bridges for users/multi-head attention mechanism/self-supervised learning/variational bipartite graph encoder分类
信息技术与安全科学引用本文复制引用
王永贵,刘丹妮..融合多个性化桥和自监督学习的跨域推荐算法[J].计算机科学与探索,2024,18(7):1792-1805,14.基金项目
国家自然科学基金(61772249).This work was supported by the National Natural Science Foundation of China(61772249). （61772249）
