Explainable recommendation based on fusion representation of multi-type feature embedding

被引:2
作者
Zheng, Jianxing [1 ]
Chen, Sen [2 ]
Cao, Feng [2 ]
Peng, Furong [2 ]
Huang, Mingqing [3 ]
机构
[1] Shanxi Univ, Inst Intelligent Informat Proc, Taiyuan 030006, Shanxi, Peoples R China
[2] Shanxi Univ, Sch Comp & Informat Technol, Taiyuan 030006, Shanxi, Peoples R China
[3] Shenzhen Inst Informat Technol, Sch Software Engn, Shenzhen 518172, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Recommender systems; Feature fusion; Score-aware embedding; Collaborative filtering; PREFERENCE;
D O I
10.1007/s11227-023-05831-x
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In e-commerce recommender systems, the sparsity of user-item rating data limits the quality of semantic embedding representation of users and items, which affects the accuracy of rating prediction. Previous studies have focused on learning attribute features or interaction features of nodes for recommendation and ignore the preference interest of rating tags in terms of attributes. In this paper, we propose a novel fusion representation method of multi-type node feature embedding for recommendation (MultiFEFR). The framework introduces rating preferences in terms of attributes and interactions and develops three kinds of feature presentations including rating-aware interaction feature embedding, rating-aware attribute feature embedding and heterogeneous attribute matched embedding. We design a multi-task joint learning strategy to optimize the accuracy of rating prediction. Experimental results show that the MultiFEFR outperforms the state-of-the-art models in MAE and RMSE metrics. Our findings are that the fusion of multi-type feature embedding can improve the accuracy of recommendation and the preference of attribute and interaction features are very explanatory for score grades.
引用
收藏
页码:10370 / 10393
页数:24
相关论文
共 55 条
[1]   A collaborative filtering recommendation algorithm based on embedding representation [J].
Alharbe, Nawaf ;
Rakrouki, Mohamed Ali ;
Aljohani, Abeer .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 215
[2]   A graph-based model to improve social trust and influence for social recommendation [J].
Bathla, Gourav ;
Aggarwal, Himanshu ;
Rani, Rinkle .
JOURNAL OF SUPERCOMPUTING, 2020, 76 (06) :4057-4075
[3]   Bias Disparity in Graph-Based Collaborative Filtering Recommenders [J].
Boltsis, Georgios ;
Pitoura, Evaggelia .
37TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, 2022, :1403-1406
[4]   A deep recommendation model of cross-grained sentiments of user reviews and ratings [J].
Cai, Yao ;
Ke, Weimao ;
Cui, Eric ;
Yu, Fei .
INFORMATION PROCESSING & MANAGEMENT, 2022, 59 (02)
[5]   Meta-relation assisted knowledge-aware coupled graph neural network for recommendation [J].
Chang, Yao ;
Zhou, Wei ;
Cai, Haini ;
Fan, Wei ;
Hu, Linfeng ;
Wen, Junhao .
INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (03)
[6]  
Cheng H., 2016, P 1 WORKSH DEEP LEAR, P7
[7]  
Cheng WY, 2020, AAAI CONF ARTIF INTE, V34, P3609
[8]   MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation [J].
Cho, Sung Min ;
Park, Eunhyeok ;
Yoo, Sungjoo .
RECSYS 2020: 14TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, 2020, :515-520
[9]   DPAN: Dynamic Preference-based and Attribute-aware Network for Relevant Recommendations [J].
Dai, Wei ;
Su, Yingmin ;
Pan, Xiaofeng ;
Wang, Yufeng ;
Zhu, Zhenyu ;
Xu, Nan ;
Mao, Chengjun ;
Cao, Bo .
PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023, 2023, :3838-3842
[10]   A Dual-Attention Autoencoder Network for Efficient Recommendation System [J].
Duan, Chao ;
Sun, Jianwen ;
Li, Kaiqi ;
Li, Qing .
ELECTRONICS, 2021, 10 (13)