Layer-wise training for self-supervised learning on graphs

End-to-end training of graph neural networks (GNN) on large graphs presents several memory and computational challenges, and limits the application to shallow architectures as depth exponentially increases the memory and space complexities. In this manuscript, we propose Layer-wise Regularized Graph Infomax, an algorithm to train GNNs layer by layer in a self-supervised manner. We decouple the feature propagation and feature transformation carried out by GNNs to learn node representations in order to derive a loss function based on the prediction of future inputs. We evaluate the algorithm in inductive large graphs and show similar performance to other end to end methods and a substantially increased efficiency, which enables the training of more sophisticated models in one single device. We also show that our algorithm avoids the oversmoothing of the representations, another common challenge of deep GNNs.

RGI : Regularized Graph Infomax for self-supervised learning on graphs

Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. We introduce \textit{Regularized Graph Infomax (RGI)}, a simple yet effective framework for node level self-supervised learning on graphs that trains a graph neural network encoder by maximizing the mutual information between node level local and global views, in contrast to previous works that employ graph level global views. The method promotes the predictability between views while regularizing the covariance matrices of the representations. Therefore, RGI is non-contrastive, does not depend on complex asymmetric architectures nor training tricks, is augmentation-free and does not rely on a two branch architecture. We run RGI on both transductive and inductive settings with popular graph benchmarks and show that it can achieve state-of-the-art performance regardless of its simplicity.