Predicting Top-${L}$ Missing Links: An Improved Local Naïve Bayes Model

Abstract

The problem of link prediction has captured considerable attention from various disciplines due to its wide range of applications. A multitude of link prediction methods have been proposed with various techniques. The local Naive Bayes (LNB) model is an effective one, which discriminates the contribution of different common neighbors by a role function. This paper proposes a new link prediction method, which further enhances the accuracy of the LNB model by considering the local community links and the degree of seed nodes. The experimental results on 12 real-world networks demonstrate that the proposed method outperforms the compared methods in the top-L link prediction task.