International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

A New Inter-layer Similarity metric for link prediction in multilayer networks

Authors :

Alireza Abdollahpouri¹ Samira Rafiee²

1- University of Kurdistan 2- University of Kurdistan

Keywords :

Link prediction, Multilayer networks, Inter-layer similarity metric, structural information

Abstract :

In real world, some networks can be modeled as a multilayer structure. In multilayer networks, a set of entities (nodes) interact with each other in complicated patterns which can involve different types of relationships (links). In these networks, the nodes are fixed in all layers, but the links in each layer are usually different. This paper, presents a new inter-layer similarity metric for predicting missing links in multilayer networks. This inter-layer similarity metric is then combined with a strong intra-layer similarity metric to improve the performance of link prediction in multilayer networks. The proposed inter-layer similarity metric uses the structural information of other layers to predict the links in a layer. Experimental results on both synthetic and real-world networks confirm the outperformance of the proposed method in terms of prediction accuracy in comparison with similar methods.