In real world, some networks can be modeled as a multilayer structure. In multilayer networks, a set of nodes interact with each other in complex 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 enhance the performance of link prediction in multilayer networks. The proposed inter-layer similarity metric uses the structural information of other layers for predicting the links in a specific 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
