AUTHOR=Hao Jiaqi , Li Zheng , Wu Zhanhe , Ma Jinming 

TITLE=Role of degree and weighted coreness based on endpoints in link prediction

JOURNAL=Frontiers in Physics

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2022.1016535

DOI=10.3389/fphy.2022.1016535

ISSN=2296-424X

ABSTRACT=Many researchers propose the link prediction models based on node similarity. Among all models, researchers find that the endpoint influence plays an important role in evaluating the similarity between endpoints. For endpoint influence, we consider that an endpoint possessing large and extensive maximum connected subgraph can strongly attract other nodes. After extensive investigations, we find that the maximum connected subgraph of an endpoint can be described though synthesizing endpoint degree and coreness, and the coreness can describe the aggregation degree of neighbors. In this paper, we propose a model by synthesizing endpoint degree and weighted coreness and make repetitive experiments on eight real benchmark datasets. The experimental results illustrate the positive role of synthetical endpoint degree and weighted coreness for measuring endpoint influence in link prediction.