Multi-task feature learning for knowledge graph enhanced recommendation

433Citations
Citations of this article
490Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by cross&compress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that cross&compress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-the-art baselines. MKR is also shown to be able to maintain satisfactory performance even if user-item interactions are sparse.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Wang, H., Zhang, F., Zhao, M., Li, W., Xie, X., & Guo, M. (2019). Multi-task feature learning for knowledge graph enhanced recommendation. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 2000–2010). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308558.3313411

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 193

84%

Researcher 19

8%

Lecturer / Post doc 14

6%

Professor / Associate Prof. 4

2%

Readers' Discipline

Tooltip

Computer Science 217

88%

Engineering 21

9%

Social Sciences 5

2%

Business, Management and Accounting 4

2%

Save time finding and organizing research with Mendeley

Sign up for free