Simple yet Effective Gradient-Free Graph Convolutional Networks

TL;DR

This paper introduces a gradient-free training framework for linearized GNNs that effectively mitigates over-smoothing, improves stability, and reduces training time in node classification tasks.

Contribution

It proposes a novel gradient-free approach to train linearized GNNs, addressing over-smoothing and enhancing efficiency and generalization.

Findings

Achieves better and more stable node classification performance.

Reduces training time significantly.

Effectively mitigates over-smoothing in deep GNNs.

Abstract

Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can achieve comparable performances on typical downstream tasks such as node classification. Although some linearized GNN variants are purposely crafted to mitigate ``over-smoothing", empirical studies demonstrate that they still somehow suffer from this issue. In this paper, we instead relate over-smoothing with the vanishing gradient phenomenon and craft a gradient-free training framework to achieve more efficient and effective linearized GNNs which can significantly overcome over-smoothing and enhance the generalization of the model. The experimental results demonstrate that our methods achieve better and more stable performances on node classification tasks with varying depths and cost much less training time.