Weisfeiler and Leman go Machine Learning: The Story so far
It synthesizes existing research on a foundational tool for graph machine learning, making it accessible for researchers and practitioners in the field.
This paper provides a comprehensive overview of how the Weisfeiler-Leman algorithm, originally a heuristic for graph isomorphism, has been adapted for machine learning with graphs and relational data, focusing on supervised learning applications.
In recent years, algorithms and neural architectures based on the Weisfeiler--Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine-learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph and node representation learning, discuss recent extensions, and outline the algorithm's connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research.