Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks

TL;DR

This paper introduces Graph structure Prompt Learning (GPL), a new method that enhances GNN training by capturing intrinsic graph structures, leading to significant performance improvements across multiple graph-related tasks.

Contribution

The paper proposes a novel GPL approach that incorporates task-independent graph structure losses to improve GNN representations and performance.

Findings

GNNs trained with GPL outperform original models by up to 24.15% on key tasks.

GPL helps GNNs capture inherent graph structures, reducing over-smoothing.

State-of-the-art results achieved on eleven real-world datasets.

Abstract

Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node and graph representations. To address this limitation, we propose a novel Graph structure Prompt Learning method (GPL) to enhance the training of GNNs, which is inspired by prompt mechanisms in natural language processing. GPL employs task-independent graph structure losses to encourage GNNs to learn intrinsic graph characteristics while simultaneously solving downstream tasks, producing higher-quality node and graph representations. In extensive experiments on eleven real-world datasets, after being trained by GPL, GNNs significantly outperform their original performance on node classification, graph classification, and edge prediction tasks (up to 10.28%, 16.5%, and 24.15%, respectively). By allowing GNNs to capture the inherent structural prompts of graphs in GPL, they can alleviate the issue of over-smooth and achieve new state-of-the-art performances, which introduces a novel and effective direction for GNN research with potential applications in various domains.