Graph neural networks are prominent models for representation learning over graph-structured data. While the capabilities and limitations of these models are well-understood for simple graphs, our understanding remains incomplete in the context of knowledge graphs. Our goal is to provide a systematic understanding of the landscape of graph neural networks for knowledge graphs pertaining to the prominent task of link prediction. Our analysis entails a unifying perspective on seemingly unrelated models and unlocks a series of other models. The expressive power of various models is characterized via a corresponding relational Weisfeiler-Leman algorithm. This analysis is extended to provide a precise logical characterization of the class of functions captured by a class of graph neural networks. The theoretical findings presented in this paper explain the benefits of some widely employed practical design choices, which are validated empirically.

翻译：图神经网络是对图结构数据进行表示学习的重要模型。尽管这些模型在简单图上的能力和局限性已被充分理解，但在知识图谱背景下我们的认知仍不完整。本文旨在系统性地理解面向知识图谱链接预测这一重要任务的图神经网络全景。我们的分析为看似无关的模型提供了统一的理论视角，并由此衍生出一系列其他模型。通过对应的关系型Weisfeiler-Leman算法，本文刻画了各类模型的表达能力，并进一步对这种分析进行拓展，给出了图神经网络所捕获函数类别的精确逻辑表征。本文的理论发现解释了若干广泛使用的实际设计选择的有效性，并通过实验进行了验证。