Deeper-GXX: Deepening Arbitrary GNNs
This work addresses a key bottleneck in GNNs for applications where deeper structures are needed, but it appears incremental as it builds on existing methods to improve training and performance.
The paper tackles the problem of training deeper graph neural networks (GNNs) by addressing vanishing gradient and over-smoothing issues, proposing Deeper-GXX with WDG-ResNet and TGCL modules, and demonstrates that it outperforms state-of-the-art deeper baselines on real-world datasets.
Recently, motivated by real applications, a major research direction in graph neural networks (GNNs) is to explore deeper structures. For instance, the graph connectivity is not always consistent with the label distribution (e.g., the closest neighbors of some nodes are not from the same category). In this case, GNNs need to stack more layers, in order to find the same categorical neighbors in a longer path for capturing the class-discriminative information. However, two major problems hinder the deeper GNNs to obtain satisfactory performance, i.e., vanishing gradient and over-smoothing. On one hand, stacking layers makes the neural network hard to train as the gradients of the first few layers vanish. Moreover, when simply addressing vanishing gradient in GNNs, we discover the shading neighbors effect (i.e., stacking layers inappropriately distorts the non-IID information of graphs and degrade the performance of GNNs). On the other hand, deeper GNNs aggregate much more information from common neighbors such that individual node representations share more overlapping features, which makes the final output representations not discriminative (i.e., overly smoothed). In this paper, for the first time, we address both problems to enable deeper GNNs, and propose Deeper-GXX, which consists of the Weight-Decaying Graph Residual Connection module (WDG-ResNet) and Topology-Guided Graph Contrastive Loss (TGCL). Extensive experiments on real-world data sets demonstrate that Deeper-GXX outperforms state-of-the-art deeper baselines.