Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting

TL;DR

This paper introduces a novel MLP-based framework called GSSC that models graph structural information without message passing, enhancing robustness and generalization in graph learning tasks.

Contribution

It proposes a simple, effective GSSC framework that leverages structural self-contrasting and sparsification, avoiding message passing in GNNs for improved robustness.

Findings

GSSC outperforms existing methods in robustness and generalization.

Structural self-contrasting effectively captures graph information without message passing.

The framework demonstrates competitive or superior performance on various graph tasks.

Abstract

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). However, most existing GNNs are based on message passing to perform feature aggregation and transformation, where the structural information is explicitly involved in the forward propagation by coupling with node features through graph convolution at each layer. As a result, subtle feature noise or structure perturbation may cause severe error propagation, resulting in extremely poor robustness. In this paper, we rethink the roles played by graph structural information in graph data training and identify that message passing is not the only path to modeling structural information. Inspired by this, we propose a simple but effective Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge to guide the computation of supervision signals, substituting the explicit message propagation as in GNNs. Specifically, it first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations. Finally, structural sparsification and self-contrasting are formulated as a bi-level optimization problem and solved in a unified framework. Extensive experiments have qualitatively and quantitatively demonstrated that the GSSC framework can produce truly encouraging performance with better generalization and robustness than other leading competitors.