Link Prediction via Graph Attention Network
This addresses the problem of low accuracy and limited hidden information extraction in link prediction for network science applications, representing an incremental improvement over existing graph deep learning methods.
The paper tackles link prediction in networks by introducing DeepLinker, a model that uses links as supervised information instead of node labels, achieving state-of-the-art accuracy on five graphs and producing efficient node representations and centrality rankings as byproducts.
Link prediction aims to infer missing links or predicting the future ones based on currently observed partial networks, it is a fundamental problem in network science with tremendous real-world applications. 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. Instead of learning node representation with the node label information, DeepLinker uses the links as supervised information. Experiments on five graphs show that DeepLinker can not only achieve the state-of-the-art link prediction accuracy, but also acquire the efficient node representations and node centrality ranking as the byproducts. Although the representations are obtained without any supervised node label information, they still perform well on node ranking and node classification tasks.