A link prediction method based on topological nearest-neighbors similarity in directed networks

Link prediction is a fundamental and key field in complex network research, and some scholars have conducted various studies in this field. However, most of the existing link prediction methods neither consider the direction of the network edge nor make full use of the information of the network node. This paper proposes a topological nearest-neighbors similarity method in a directed network to solve this problem. Firstly, this study improved the Sorensen index in directed networks, and its variants also are proposed. Secondly, the matrix form of each basic index is expressed using matrix algebra. Then, based on the idea of GLHN(Global Leicht Holme Newman) similarity index, the nearest-neighbors topology of each basic index is derived to obtain the topological nearest -neighbors similarity index. Finally, the proposed method is validated empirically using multiple real directed network datasets. Experiments verify the superiority of the proposed method by comprehensively using three evaluation metrics compared with the benchmark indices, including lower error, higher accuracy and stronger robustness.

Automated summary

Link prediction is a fundamental and key field in complex network research. This paper proposes a topological nearest-neighbors similarity method in a directed network to tackle the limitations of existing methods. The proposed method shows better performance in terms of lower error, higher accuracy, and stronger robustness through empirical validation on multiple real directed network datasets.