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.

图神经网络 (GNN) 的端对端训练在大型图上存在多个存储和计算上的挑战，通过自监督的方式，我们提出了逐层规则化图信息最大化算法以逐层训练 GNN，通过解耦特征传播和特征转换来学习节点表示，从而得出基于对未来输入预测的损失函数。我们在归纳大型图上评估了算法，并展示了类似于其他端对端方法的性能，以及大幅提高的效率，使得能够在一个设备上训练更复杂的模型。我们还展示了我们的算法避免了表示过度平滑的问题，这是深度 GNN 的另一个常见挑战。