AUTHOR=Kong Yixiu , Hu Yizhong , Zhang Xinyu , Wang Cheng 

TITLE=Structural centrality of networks can improve the diffusion-based recommendation algorithm

JOURNAL=Frontiers in Physics

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2022.1018781

DOI=10.3389/fphy.2022.1018781

ISSN=2296-424X

ABSTRACT=Recommendation system has become an indispensable information technology in real world. The recommendation system based on diffusion model has been widely used because of its simplicity, scalability, interpretability and many other advantages. However, the traditional diffusion-based recommendation model only uses the nearest neighbor information. which limits its efficiency and performance. Therefore, in this paper, we introduce the centrality of complex networks into the diffusion-based recommendation system, and test its performance. The results show that the accuracy of Heat-Conduction algorithm can be improved by two times by introducing the centrality of complex networks, reaching almost the same level as Mass-diffusion algorithm. Therefore, the recommendation system combining high-order network structure information is a potentially promising research direction in the future.