Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs. However, in addition to their reliance on elaborate architectures and algorithms, there are several key technical details that are frequently overlooked, and yet nonetheless can play a vital role in achieving satisfactory performance. In this paper, we first summarize a series of existing tricks-of-the-trade, and then propose several new ones related to label usage, loss function formulation, and model design that can significantly improve various GNN architectures. We empirically evaluate their impact on final node classification accuracy by conducting ablation studies and demonstrate consistently-improved performance, often to an extent that outweighs the gains from more dramatic changes in the underlying GNN architecture. Notably, many of the top-ranked models on the Open Graph Benchmark (OGB) leaderboard and KDDCUP 2021 Large-Scale Challenge MAG240M-LSC benefit from these techniques we initiated.
翻译:过去几年来,图形神经网络(GNN)和基于传播的标签方法在处理图表节点分类任务方面取得了显著进展,然而,除了依赖精心设计的架构和算法之外,还有一些关键技术细节经常被忽视,但在实现令人满意的业绩方面可以发挥重要作用。在本文中,我们首先总结了一系列现有的贸易技巧,然后提出了几个与标签使用、损失函数配置和模型设计有关的新技巧,从而可以大大改进各种GNN结构。我们通过进行通缩研究,实证地评估了它们对最终节点分类准确性的影响,并展示了一贯改进的性能,其程度往往超过GNNM基本架构更显著变化的成果。值得注意的是,公开图表基准(OGB)领导板和KDDCUP 2021大比例挑战MAG240M-LSC的许多模型受益于我们发起的这些技术。