Link Prediction via Deep Learning
share
Link prediction aims to infer the missing links or predicting future ones based on the currently observed partial network. It is a fundamental problem in network science because not only the problem has wide range of applications such as social network recommendation and information retrieval, but also the linkages contain rich hidden information of node properties and network structures. However, conventional link prediction approaches neither have high prediction accuracy nor being capable of revealing the hidden information behind links. To address this problem, we generalize the latest techniques in deep learning on graphs and present a new link prediction model - DeepLinker by integrating the batched graph convolution techniques in GraphSAGE and the attention mechanism in graph attention network (GAT). Experiments on five graphs show that our model can not only achieve the state-of-the-art accuracy in link prediction, but also the efficient ranking and node representations as the byproducts of link prediction task. Although the low dimensional node representations are obtained without any node label information, they can perform very well on downstream tasks such as node ranking and classification. Therefore, we claim that the link prediction task on graphs is like the language model in natural language processing because it reveals the hidden information from the graph structure in an unsupervised way.
READ FULL TEXT