Link Prediction Based on Pairwise Proximity Preserving Graph Neural Networks

Link prediction is one of the key problems in network science and can be applied to many scenarios such as recommender system. Traditional link prediction methods are either based on heuristics or shallow network embedding methods which may either hardly generalize well or cannot optimize node representations and link probabilities simultaneously. Although the recently proposed graph neural network-based methods achieve promising performances, they do not preserve the original pairwise proximity at each hidden layer since non-linear operations may hinder it. In this paper, we propose a novel end-to-end link prediction method named Pairwise Proximity Preserving Graph neural network (PPPG), which can preserve the pairwise proximity at each layer. Specifically, inspired by graph signal denoising techniques, we preserve the structural pairwise proximity by solving an optimization problem after the nonlinear operations at each layer. We evaluate our model on various standard link prediction benchmarks, and obtain competitive results.