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

Morris, Christopher; Fey, Matthias; Kriege, Nils

doi:10.24963/ijcai.2021/618

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

Christopher Morris, Matthias Fey, Nils Kriege

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Survey Track. Pages 4543-4550.

https://doi.org/10.24963/ijcai.2021/618

Keywords

Machine learning: General

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.

Christopher Morris, Matthias Fey, and Nils Kriege. 2021. The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4543–4550. https://doi.org/10.24963/ijcai.2021/618

@inproceedings{ijcai2021p618,
  title     = {The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs},
  author    = {Morris, Christopher and Fey, Matthias and Kriege, Nils},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {4543--4550},
  year      = {2021},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2021/618},
  url       = {https://doi.org/10.24963/ijcai.2021/618},
}

TY  - CPAPER
TI  - The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs
AU  - Morris, Christopher
AU  - Fey, Matthias
AU  - Kriege, Nils
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 4543
EP  - 4550
DO  - 10.24963/ijcai.2021/618
UR  - https://doi.org/10.24963/ijcai.2021/618
ER  -