Neural variational collaborative filtering with side information for top-K recommendation

doi:10.1007/s13042-019-01016-2

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Neural variational collaborative filtering with side information for top-K recommendation
	Deng, Xiaoyi 1,2; Zhuang, Fuzhen 3,4,5; Zhu, Zhiguo 6
刊名	INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
	2019-11-01
卷号	10 期号:11 页码:3273-3284
关键词	Neural collaborative filtering Variational autoencoder Top-K recommendation Side information Implicit feedback
ISSN号	1868-8071
DOI	10.1007/s13042-019-01016-2
英文摘要	Collaborative filtering (CF) is one of the most widely applied models for recommender systems. Despite its success, CF-based methods suffer from rating sparsity and cold-start problem, which leads to poor quality of recommendations. Previous studies have gave great attention to construct hybrid methods, by incorporating side information and user rating. Variational autoencoder (VAE) has been confirmed to be highly effective in CF task, due to its Bayesian nature and non-linearity. However, rating sparsity remains a great challenge to most VAE models, which leads to poor latent user/item representations. In addition, most existing VAE-based methods model either latent user factors or latent item factors, resulting in the incapacity to recommend items to a new user or suggest a new item to existing users. To address these problems, we design a novel deep hybrid framework for top-k recommendation, neural variational collaborative filtering (NVCF), and propose three NVCF-based instantiation. In generative process, the side information of user and item is incorporated to alleviate rating sparsity, for learning better latent user/item representations. In inference process, a Stochastic Gradient Variational Bayes approach is employed to approximate the unmanageable distributions of latent user/item factors. Experiments performed on four public datasets have indicated our methods significantly outperform the state-of-the-art hybrid CF models and VAE-based methods.
资助项目	National Natural Science Foundation of China[71401058] ; National Natural Science Foundation of China[71672023] ; National Natural Science Foundation of China[61773361] ; Program for New Century Excellent Talents in Fujian Province University (NCETFJ)
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER HEIDELBERG
WOS记录号	WOS:000494802500021
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/14829]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Deng, Xiaoyi
作者单位	1.Huaqiao Univ, Sch Business, Quanzhou 362021, Fujian, Peoples R China 2.Huaqiao Univ, Res Ctr Appl Stat & Big Data, Xiamen 361021, Fujian, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Zhengzhou Univ, Sch Informat Engn, Zhengzhou 450001, Henan, Peoples R China 5.Zhengzhou Univ, Res Ctr Digital Med Image Tech, Zhengzhou 450001, Henan, Peoples R China 6.Dongbei Univ Finance & Econ, Sch Management Sci & Engn, Dalian 116025, Peoples R China
推荐引用方式 GB/T 7714	Deng, Xiaoyi,Zhuang, Fuzhen,Zhu, Zhiguo. Neural variational collaborative filtering with side information for top-K recommendation[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2019,10(11):3273-3284.
APA	Deng, Xiaoyi,Zhuang, Fuzhen,&Zhu, Zhiguo.(2019).Neural variational collaborative filtering with side information for top-K recommendation.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,10(11),3273-3284.
MLA	Deng, Xiaoyi,et al."Neural variational collaborative filtering with side information for top-K recommendation".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 10.11(2019):3273-3284.