SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

TL;DR

This paper introduces Skipnode, a simple plug-and-play module that alleviates performance degradation in deep Graph Convolutional Networks by selectively skipping nodes during convolution, effectively addressing over-smoothing and gradient vanishing.

Contribution

The paper proposes Skipnode, a novel method that improves deep GCN performance by sampling nodes to skip convolutions, backed by theoretical analysis and empirical validation.

Findings

Skipnode effectively suppresses over-smoothing and gradient vanishing.

Skipnode outperforms state-of-the-art baselines in deep GCNs.

Theoretical analysis confirms the benefits of node skipping in deep GCNs.

Abstract

Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs: over-smoothing and gradient vanishing have a mutually reinforcing effect that causes the performance to deteriorate more quickly in deep GCNs. On the other hand, existing anti-over-smoothing methods all perform full convolutions up to the model depth. They could not well resist the exponential convergence of over-smoothing due to model depth increasing. In this work, we propose a simple yet effective plug-and-play module, Skipnode, to overcome the performance degradation of deep GCNs. It samples graph nodes in each convolutional layer to skip the convolution operation. In this way, both over-smoothing and gradient vanishing can be effectively suppressed since (1) not all nodes'features propagate through full layers and, (2) the gradient can be directly passed back through ``skipped'' nodes. We provide both theoretical analysis and empirical evaluation to demonstrate the efficacy of Skipnode and its superiority over SOTA baselines.