Much of the recent progress made in node classification on graphs can be credited to the careful design on graph neural networks (GNN) and label propagation algorithms. However, in the literature, in addition to improvements to the model architecture, there are a number of improvements either briefly mentioned as implementation details or visible only in source code, and these overlooked techniques may play a pivotal role in their practical use. In this paper, we first summarize a collection of existing refinements, and then propose several novel techniques regarding these model designs and label usage. We empirically evaluate their impacts on the final model accuracy through ablation studies, and show that we are able to significantly improve various GNN models to the extent that they outweigh the gains from model architecture improvement. Notably, many of the top-ranked models on Open Graph Benchmark benefit from our techniques.

本文概述了一系列现有的技巧，并提出了一些与标签使用、损失函数制定和模型设计相关的新技巧，以显著提高各种图神经网络(GNN)架构的性能。通过进行消融研究，我们经验性地评估了它们对最终节点分类精度的影响，并证明了它们的性能得到了不断改进，通常超过了底层GNN架构变化所带来的收益。值得注意的是，许多排名前列的模型从中受益，这是我们提出的一些技术。

基于图神经网络的节点分类的增强方法