Welcome to the InfoSci Platform
Reference Hub7
Scholar Recommendation Based on High-Order Propagation of Knowledge Graphs

Scholar Recommendation Based on High-Order Propagation of Knowledge Graphs

Pu Li, Tianci Li, Xin Wang, Suzhi Zhang, Yuncheng Jiang, Yong Tang
Copyright: © 2022 |Volume: 18 |Issue: 1 |Pages: 19
ISSN: 1552-6283|EISSN: 1552-6291|EISBN13: 9781799893967|DOI: 10.4018/IJSWIS.297146
Cite Article Cite Article

MLA

Li, Pu, et al. "Scholar Recommendation Based on High-Order Propagation of Knowledge Graphs." IJSWIS vol.18, no.1 2022: pp.1-19. http://doi.org/10.4018/IJSWIS.297146

APA

Li, P., Li, T., Wang, X., Zhang, S., Jiang, Y., & Tang, Y. (2022). Scholar Recommendation Based on High-Order Propagation of Knowledge Graphs. International Journal on Semantic Web and Information Systems (IJSWIS), 18(1), 1-19. http://doi.org/10.4018/IJSWIS.297146

Chicago

Li, Pu, et al. "Scholar Recommendation Based on High-Order Propagation of Knowledge Graphs," International Journal on Semantic Web and Information Systems (IJSWIS) 18, no.1: 1-19. http://doi.org/10.4018/IJSWIS.297146

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In a big data environment, traditional recommendation methods have limitations such as data sparseness and cold start, etc. In view of the rich semantics, excellent quality, and good structure of knowledge graphs, many researchers have introduced knowledge graphs into the research about recommendation systems, and studied interpretable recommendations based on knowledge graphs. Along this line, this paper proposes a scholar recommendation method based on the high-order propagation of knowledge graph (HoPKG), which analyzes the high-order semantic information in the knowledge graph, and generates richer entity representations to obtain users’ potential interest by distinguishing the importance of different entities. On this basis, a dual aggregation method of high-order propagation is proposed to enable entity information to be propagated more effectively. Through experimental analysis, compared with some baselines, such as Ripplenet, RKGE and CKE, our method has certain advantages in the evaluation indicators AUC and F1.