arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.02209cs.LGcs.AI
收藏

基于关系Weisfeiler-Leman的知识图谱链接预测理论

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

University of Oxford(牛津大学);Universidad Católica de Chile(智利天主教大学);CENIA Chile(智利国家人工智能中心);IMFD Chile(智利复杂工程系统研究所)

Xingyue Huang, Miguel Romero Orth, İsmail İlkan Ceylan, Pablo Barceló

AI总结:

本文通过关系Weisfeiler-Leman算法统一分析知识图谱链接预测中的图神经网络模型,刻画其表达能力并给出逻辑刻画,从理论和实验上解释了常用设计选择的优势。

摘要:

图神经网络是图结构数据表示学习的突出模型。虽然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,我们的理解仍不完整。我们的目标是对面向链接预测这一重要任务的知识图谱图神经网络格局提供系统性理解。我们的分析为看似无关的模型提供了统一视角,并揭示了一系列其他模型。各种模型的表达能力通过相应的关系Weisfeiler-Leman算法来刻画。该分析进一步扩展,为某一类图神经网络所捕获的函数类提供了精确的逻辑刻画。本文提出的理论发现解释了一些广泛采用的实用设计选择的优势,并通过实验进行了验证。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑