Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate set into a space and selectively samples from this space to generate negative samples. To further enhance the diversity of the negative samples during each forward pass, we develop a space-squeezing method to achieve layer-wise diversity in multi-layer GNNs. Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance. Moreover, adding negative samples dynamically changes the graph's topology, thus with the strong potential to improve the expressiveness of GNNs and reduce the risk of over-squashing.

翻译：图神经网络（GNNs）凭借其对图数据的强大表征能力，成为各类结构学习应用的有效解决方案。然而，传统GNNs依赖仅从一阶邻居（即正样本）收集信息的信息传递机制，可能导致过度平滑与过度挤压等问题。为缓解这些问题，我们提出一种面向信息传递传播的层多样负采样方法。该方法在行列式点过程中引入采样矩阵，将候选集映射至特征空间，并从中选择性采样生成负样本。为增强前向传播过程中负样本的多样性，我们进一步开发空间压缩方法，实现多层GNNs的逐层多样性。在多种真实图数据集上的实验表明，本方法能有效提升负样本多样性及整体学习性能。此外，动态添加负样本可改变图拓扑结构，从而具备提升GNNs表达能力并降低过度挤压风险的显著潜力。