Link Prediction via Graph Attention Network
arXiv:1910.04807
Abstract
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.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Emergence of scaling in random networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Hierarchical structure and the prediction of missing links in networks
- Predicting Missing Links via Local Information
- struc2vec: Learning Node Representations from Structural Identity
- Quantifying Long-Term Scientific Impact
- Popularity versus Similarity in Growing Networks
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- A Convolutional Encoder Model for Neural Machine Translation