An integrated model based on deep multimodal and rank learning for point-of-interest recommendation

被引:10
作者
Liao, Jianxin [1 ]
Liu, Tongcun [1 ]
Yin, Hongzhi [2 ]
Chen, Tong [2 ]
Wang, Jingyu [1 ]
Wang, Yulong [1 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing, Peoples R China
[2] Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane, Qld, Australia
来源
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS | 2021年 / 24卷 / 02期
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
POI recommendation; content-aware; deep multimodal networks; rank learning; cold-start;
D O I
10.1007/s11280-021-00865-8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Modeling point-of-Interest (POI) for recommendations is vital in location-based social networks, yet it is a challenging task due to data sparsity and cold-start problems. Most existing approaches incorporate content features into a probabilistic matrix factorization model using unsupervised learning, which results in inaccuracy and weak robustness of recommendations when data is sparse, and the cold-start problems remain unsolved. In this paper, we propose a deep multimodal rank learning (DMRL) model that improves both the accuracy and robustness of POI recommendations. DMRL exploits temporal dynamics by allowing each user to have time-dependent preferences and captures geographical influences by introducing spatial regularization to the model. DMRL jointly learns ranking for personal preferences and supervised deep learning models to create a semantic representation of POIs from multimodal content. To make model optimization converge more rapidly while preserving high effectiveness, we develop a ranking-based dynamic sampling strategy to sample adverse or negative POIs for model training. We conduct experiments to compare our DMRL model with existing models that use different approaches using two large-scale datasets obtained from Foursquare and Yelp. The experimental results demonstrate the superiority of DMRL over the other models in creating cold-start POI recommendations and achieving excellent and highly robust results for different degrees of data sparsity.
引用
收藏
页码:631 / 655
页数:25
相关论文
共 48 条
[1]   AIR: Attentional Intention-Aware Recommender Systems [J].
Chen, Tong ;
Yin, Hongzhi ;
Chen, Hongxu ;
Yan, Rui ;
Quoc Viet Hung Nguyen ;
Li, Xue .
2019 IEEE 35TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2019), 2019, :304-315
[2]  
Cheng C, 2012, PROC 26 AAAI C ARTIF, P17
[3]  
Feng SS, 2015, PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), P2069
[4]  
Gao HJ, 2015, AAAI CONF ARTIF INTE, P1721
[5]   CoSoLoRec: Joint Factor Model with Content, Social, Location for Heterogeneous Point-of-Interest Recommendation [J].
Guo, Hao ;
Li, Xin ;
He, Ming ;
Zhao, Xiangyu ;
Liu, Guiquan ;
Xu, Guandong .
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2016, 2016, 9983 :613-627
[6]   Streaming Session-based Recommendation [J].
Guo, Lei ;
Yin, Hongzhi ;
Wang, Qinyong ;
Chen, Tong ;
Zhou, Alexander ;
Nguyen Quoc Viet Hung .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :1569-1577
[7]  
He J, 2017, PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P1837
[8]  
He RN, 2016, AAAI CONF ARTIF INTE, P144
[9]   Convolutional Matrix Factorization for Document Context-Aware Recommendation [J].
Kim, Donghyun ;
Park, Chanyoung ;
Oh, Jinoh ;
Lee, Sungyoung ;
Yu, Hwanjo .
PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, :233-240
[10]   Two Birds One Stone: On both Cold-Start and Long-Tail Recommendation [J].
Li, Jingjing ;
Lu, Ke ;
Huang, Zi ;
Shen, Heng Tao .
PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, :898-906