---
title: "The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs"
authors:
  - "Christopher Morris"
  - "Matthias Fey"
  - "Nils Kriege"
doi: "10.24963/ijcai.2021/618"
url: "https://ijcai.org/proceedings/2021/618"
pdf: "https://ijcai.org/proceedings/2021/0618.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4543-4550"
track: "Survey Track"
keywords:
  - "Machine learning: General"
---

# The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs

Christopher Morris, Matthias Fey, Nils Kriege

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4543-4550. DOI: [10.24963/ijcai.2021/618](https://doi.org/10.24963/ijcai.2021/618)

## Abstract

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for (supervised) machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine learning setting. We discuss the theoretical background, show how to use it for supervised graph- and node classification, discuss recent extensions, and its connection to neural architectures. Moreover, we give an overview of current applications and future directions to stimulate research.