Graph neural networks (GNNs) are widely used in the applications based on graph structured data, such as node classification and link prediction. However, GNNs are often used as a black-box tool and rarely get in-depth investigated regarding whether they fit certain applications that may have various properties. A recently proposed technique distance encoding (DE) (Li et al. 2020) magically makes GNNs work well in many applications, including node classification and link prediction. The theory provided in (Li et al. 2020) supports DE by proving that DE improves the representation power of GNNs. However, it is not obvious how the theory assists the applications accordingly. Here, we revisit GNNs and DE from a more practical point of view. We want to explain how DE makes GNNs fit for node classification and link prediction. Specifically, for link prediction, DE can be viewed as a way to establish correlations between a pair of node representations. For node classification, the problem becomes more complicated as different classification tasks may hold node labels that indicate different physical meanings. We focus on the most widely-considered node classification scenarios and categorize the node labels into two types, community type and structure type, and then analyze different mechanisms that GNNs adopt to predict these two types of labels. We run extensive experiments to compare eight different configurations of GNNs paired with DE to predict node labels over eight real-world graphs. The results demonstrate the uniform effectiveness of DE to predict structure-type labels. Lastly, we reach three pieces of conclusions on how to use GNNs and DE properly in node classification tasks.

中文翻译：

---

在实际视图中重温图神经网络和距离编码

图神经网络（GNN）广泛用于基于图结构化数据的应用程序中，例如节点分类和链接预测。但是，GNN通常被用作黑盒工具，很少对其是否适合某些可能具有各种属性的应用进行深入研究。最近提出的技术距离编码（DE）（Li et al.2020）神奇地使GNN在许多应用中都能很好地工作，包括节点分类和链接预测。（Li et al.2020）中提供的理论通过证明DE提高了GNN的表示能力来支持DE。但是，该理论如何相应地辅助应用尚不清楚。在这里，我们从更实际的角度重新审视GNN和DE。我们想解释一下DE如何使GNN适合节点分类和链接预测。特别，对于链路预测，可以将DE视为在一对节点表示之间建立相关性的方法。对于节点分类，由于不同的分类任务可能持有表示不同物理含义的节点标签，因此问题变得更加复杂。我们关注于最广泛考虑的节点分类方案，并将节点标签分为社区类型和结构类型两种类型，然后分析GNN用来预测这两种类型标签的不同机制。我们进行了广泛的实验，以比较GDE与DE配对的八种不同配置，以预测八幅现实世界中的节点标签。结果证明了DE预测结构类型标签的统一有效性。最后，