Predicting new links in a network is a problem of interest in many application domains. Most of the prediction methods utilize information on the network’s entities such as nodes to build a model of links. Network structures are usually not used except for the networks with similarity or relatedness semantics. In this work, we use network structures for link prediction with a more general network type with latent feature models. The problem is the difficulty to train these models directly for large data. We propose a method to solve this problem using kernels and cast the link prediction problem into a binary classification problem. The key idea is not to infer latent features explicitly, but to represent these features implicitly in the kernels, making the method scalable to large networks. In contrast to the other methods for latent feature models, our method inherits all the advantages of kernel framework: optimality, efficiency and nonlinearity. We apply our method to real data of protein-protein interactions to show the merits of our method.