GPL_Dataset

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 \textbf{G}raph structure \textbf{P}rompt \textbf{L}earning 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.

图神经网络（GNNs）在图数据建模领域得到广泛应用。然而，现有的GNNs往往以任务驱动的方式进行训练，这未能充分捕捉图结构的内在本质，从而导致节点和图表示的次优。为了解决这一局限，我们提出了一种新颖的图结构提示学习方法（Graph Structure Prompt Learning, 简称GPL），以提升GNNs的训练效果，该方法灵感源自自然语言处理中的提示机制。GPL采用任务无关的图结构损失函数，鼓励GNNs在学习内在图特征的同时解决下游任务，从而生成更高品质的节点和图表示。在基于十一个真实世界数据集的广泛实验中，经过GPL训练的GNNs在节点分类、图分类和边预测任务上的表现显著优于其原始性能（分别提升了10.28%、16.5%和24.15%）。通过使GNNs在GPL中捕捉图的固有结构提示，它们能够缓解过度平滑的问题，并实现新的最先进性能，这为GNN研究开辟了新颖而有效的方向，并具有在各个领域潜在的应用价值。