Graph Neural Networks (GNNs) have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and found that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation method, comprising DP-Noise and DP-Mask, which adeptly retains essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.

翻译：图神经网络已成为处理图数据的首选工具，其性能通过图数据增强技术得到提升。尽管增强方法不断演进，但仍存在图属性失真和结构变化受限等问题。这引出一个关键问题：能否开发出更保属性且对结构变化更敏感的增强方法？通过频谱分析视角，我们探究了图属性、增强方法及其频谱特性之间的相互作用，发现保持低频特征值不变可在生成增强图时大规模保留关键属性。基于这些发现，我们提出双棱镜增强方法，包含双棱镜噪声与双棱镜掩码两种变体，该方法能在增强图多样化的同时巧妙保留关键图属性。大量实验验证了我们方法的有效性，为图数据增强提供了新的研究方向。