Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations

doi:10.1109/ACCESS.2018.2874959

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 平行控制

	Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations
	Lin, Qika 1; Niu, Yaoqiang 2; Zhu, Yifan 1; Lu, Hao 1,3; Mushonga, Keith Zvikomborero 1; Niu, Zhendong 1,4
刊名	IEEE ACCESS
	2018
卷号	6 页码:58990-59000
关键词	Heterogeneous knowledge data embedding entity representation attentive neural networks short-term music recommendation
ISSN号	2169-3536
DOI	10.1109/ACCESS.2018.2874959
通讯作者	Niu, Zhendong(zniu@bit.edu.cn)
英文摘要	The current existing data in online music service platforms are heterogeneous, extensive, and disorganized. Finding an effective method to use these data in recommending appropriate music to users during a short-term session is a significant challenge. Another serious problem is that most of the data, in reality, obey the long-tailed distribution, which consequently leads to traditional music recommendation systems recommending a lot of popular music that users do not like on a specific occasion. To solve these problems, we propose a heterogeneous knowledge-based attentive neural network model for short-term music recommendations. First, we collect three types of data for modeling entities in user-music interaction network, i.e., graphic, textual, and visual data, and then embed them into high-dimensional spaces using the TransR, distributed memory version of paragraph vector, and variational autoencoder methods, respectively. The concatenation of these embedding results is an abstract representation of the entity. Based on this, a recurrent neural network with an attention mechanism is built, which is capable of obtaining users' preferences in the current session and consequently making recommendations. The experimental results show that our proposed approach outperforms the current state-of-the-art short-term music recommendation systems on one real-world dataset. In addition, it can also recommend more relatively unpopular songs compared with classic models.
资助项目	National Natural Science Foundation of China[61370137] ; Ministry of Education-China Mobile Research Foundation Project[2016/2-7]
WOS关键词	CHALLENGES ; SYSTEM
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000449548300001
资助机构	National Natural Science Foundation of China ; Ministry of Education-China Mobile Research Foundation Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/22608]
专题	复杂系统管理与控制国家重点实验室_平行控制
通讯作者	Niu, Zhendong
作者单位	1.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 10081, Peoples R China 2.Lanzhou Jiaotong Univ, Sch Comp Technol, Lanzhou 730000, Gansu, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.Univ Pittsburgh, Sch Comp & Informat, Pittsburgh, PA 15260 USA
推荐引用方式 GB/T 7714	Lin, Qika,Niu, Yaoqiang,Zhu, Yifan,et al. Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations[J]. IEEE ACCESS,2018,6:58990-59000.
APA	Lin, Qika,Niu, Yaoqiang,Zhu, Yifan,Lu, Hao,Mushonga, Keith Zvikomborero,&Niu, Zhendong.(2018).Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations.IEEE ACCESS,6,58990-59000.
MLA	Lin, Qika,et al."Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations".IEEE ACCESS 6(2018):58990-59000.