NeurIPS 2023poster25 citations

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.

graph neural networksknowledge graphsexpressivitylogical characterization
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}
}
A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs · NeurIPS 2023