Mitigating Data Sparsity Using Similarity Reinforcement-Enhanced Collaborative Filtering

被引:36
作者
Hu, Yan [1 ,2 ,4 ]
Shi, Weisong [2 ]
Li, Hong [3 ]
Hu, Xiaohui [4 ]
机构
[1] Univ Chinese Acad Sci, Beijing, Peoples R China
[2] Wayne State Univ, Dept Comp Sci, 5057 Woodward Ave,Suite 14102-2, Detroit, MI 48202 USA
[3] Chinese Acad Sci, Inst Informat Engn, 89 Minzhuang Rd, Beijing, Peoples R China
[4] Chinese Acad Sci, Inst Software, 4 South Fourth St, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Recommender system; rating prediction; personalization; data sparsity; similarity reinforcement; MATRIX FACTORIZATION;
D O I
10.1145/3062179
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The data sparsity problem has attracted significant attention in collaborative filtering-based recommender systems. To alleviate data sparsity, several previous efforts employed hybrid approaches that incorporate auxiliary data sources into recommendation techniques, like content, context, or social relationships. However, due to privacy and security concerns, it is generally difficult to collect such auxiliary information. In this article, we focus on the pure collaborative filtering methods without relying on any auxiliary data source. We propose an improved memory-based collaborative filtering approach enhanced by a novel similarity reinforcement mechanism. It can discover potential similarity relationships between users or items by making better use of known but limited user-item interactions, thus to extract plentiful historical rating information from similar neighbors to make more reliable and accurate rating predictions. This approach integrates user similarity reinforcement and item similarity reinforcement into a comprehensive framework and lets them enhance each other. Comprehensive experiments conducted on several public datasets demonstrate that, in the face of data sparsity, our approach achieves a significant improvement in prediction accuracy when compared with the state-of-the-art memory-based and model-based collaborative filtering algorithms.
引用
收藏
页数:20
相关论文
共 57 条
[1]   A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem [J].
Ahn, Hyung Jun .
INFORMATION SCIENCES, 2008, 178 (01) :37-51
[2]  
[Anonymous], P 27 ANN INT C RES D, DOI DOI 10.1145/1008992.1009051
[3]  
[Anonymous], 2011, INTRO RECOMMENDER SY
[4]  
Bergner Yoav., 2012, P 5 INT C ED DAT MIN, P95
[5]  
Breese J. S., 1998, Uncertainty in Artificial Intelligence. Proceedings of the Fourteenth Conference (1998), P43
[6]  
Canny J., 2002, Proceedings of SIGIR 2002. Twenty-Fifth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, P238, DOI 10.1145/564376.564419
[7]  
Celma O, 2010, MUSIC RECOMMENDATION AND DISCOVERY, P1, DOI 10.1007/978-3-642-13287-2
[8]   A Fast Parallel Stochastic Gradient Method for Matrix Factorization in Shared Memory Systems [J].
Chin, Wei-Sheng ;
Zhuang, Yong ;
Juan, Yu-Chin ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2015, 6 (01)
[9]   Item-based top-N recommendation algorithms [J].
Deshpande, M ;
Karypis, G .
ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2004, 22 (01) :143-177
[10]   Enhancing memory-based collaborative filtering for group recommender systems [J].
Ghazarian, Sarik ;
Nematbakhsh, Mohammad Ali .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (07) :3801-3812