A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
Xingyue Huang, Miguel Romero Orth, Ismail Ilkan Ceylan, Pablo Barcelo
Abstract
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.
BibTeX
@inproceedings{
huang2023a,
title={A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs},
author={Xingyue Huang and Miguel Romero Orth and Ismail Ilkan Ceylan and Pablo Barcelo},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=7hLlZNrkt5}
}