Weisfeiler and Leman Go Relational

Pablo Barcelo, Mikhail Galkin, Christopher Morris, Miguel Romero

Research output: Contribution to journalConference articlepeer-review


Knowledge graphs, modeling multi-relational data, improve numerous applications such as question answering or graph logical reasoning. Many graph neural networks for such data emerged recently, often outperforming shallow architectures. However, the design of such multi-relational graph neural networks is ad-hoc, driven mainly by intuition and empirical insights. Up to now, their expressivity, their relation to each other, and their (practical) learning performance is poorly understood. Here, we initiate the study of deriving a more principled understanding of multi-relational graph neural networks. Namely, we investigate the limitations in the expressive power of the well-known Relational GCN and Compositional GCN architectures and shed some light on their practical learning performance. By aligning both architectures with a suitable version of the Weisfeiler-Leman test, we establish under which conditions both models have the same expressive power in distinguishing non-isomorphic (multi-relational) graphs or vertices with different structural roles. Further, by leveraging recent progress in designing expressive graph neural networks, we introduce the k-RN architecture that provably overcomes the expressiveness limitations of the above two architectures. Empirically, we confirm our theoretical findings in a vertex classification setting over small and large multi-relational graphs.

Original languageEnglish
JournalProceedings of Machine Learning Research
StatePublished - 2022
Externally publishedYes
Event1st Learning on Graphs Conference, LOG 2022 - Virtual, Online
Duration: 9 Dec 202212 Dec 2022


Dive into the research topics of 'Weisfeiler and Leman Go Relational'. Together they form a unique fingerprint.

Cite this