Journal
IEEE ACCESS
Volume 7, Issue -, Pages 9384-9394Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2891513
Keywords
Recommender systems; computer science; data mining; information processing; information technology
Categories
Funding
- National Natural Science Foundation of China [61303167, 61702306, 61433012, U1435215, 71772107, 71704096]
- Ministry of Education Foundation for Humanities and Social Sciences in China [17YJCZH262, 16YJCZH041, 16YJCZH154, 16YJCZH012, 18YJAZH136]
- National Key RD Plan in China [2018YFC0831002]
- Key Project of Industrial Transformation and Upgrading in China [TC170A5SW]
- Natural Science Foundation of Shandong Province [ZR2018BF013, ZR2017BF015]
- Innovative Research Foundation of Qingdao [18-2-2-41-jch]
- Key R&D Plan of Shandong Province [2018GGX101045]
- Shandong Education Quality Improvement Plan for Postgraduate
Ask authors/readers for more resources
Matrix factorization is a widely used technique in recommender systems. However, its performance is often affected by the sparsity and the scalability. To address the above-mentioned problem, we propose an interpretable and scalable recommendation method based on network embedding (ISRM_NE) in this paper. First, a novel user-item co-occurrence network is presented, which reflects both the user's preferences and the co-occurrence relationship among items. Second, the conceptions of tightness and equivalence are given to describe the structural similarity in the network, which can explore four relationships in recommender system: user's preference, item co-occurrence relationship, user's potential preference, and similarity between users. Finally, two sampling strategies are combined to traverse the network so as to get the latent vector of items and users through network representation learning. Thus, the top-N recommendation can be achieved by vector computing. The proposed method called ISRM_NE improves the performance of the recommender system in terms of interpretability and scalability. Moreover, extensive experiments on two real-world datasets demonstrate that the ISRM_NE outperforms three popular methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available