A Link Prediction Algorithm Based on GAN

Link prediction, as an important research direction in complicated network analysis, has broad application prospects. However, traditional link prediction algorithms are generally designed by the sparse expression of adjacency matrix, which is computationally expensive and inefficient, being also unable to run on large-scale networks preserve their higher order structural features. To fill this gap, we propose a GAN (generative adversarial network)-based algorithm. The algorithm layers graph, preserving local features higher-level original uses generative model recursively backwardly obtain low-dimensional vector form vertices each layer graph initialization previous layer. It then obtains all for problem minima that can be generated random solved. experimental results show our method superior many state-of-the-art algorithms.