Weisfeiler and Leman go Machine Learning: The Story so far
Copyright policy )Weisfeiler and Leman go Machine Learning: The Story so far
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.
Journal of Machine Learning Research, 24
ISSN:1532-4435
ISSN:1533-7928
- Technical University of Munich Germany
- Universität Wien Austria
- ETH Zurich Switzerland
- RWTH Aachen University Germany
- University of Vienna Austria
FOS: Computer and information sciences, Computer Science - Machine Learning, Machine learning for graphs; Graph neural networks; Weisfeiler-Leman algorithm; expressivity; equivariance, cs.LG, Machine Learning (stat.ML), 102019 Machine learning, expressivity, Machine Learning (cs.LG), 102031 Theoretische Informatik, Statistics - Machine Learning, Computer Science - Data Structures and Algorithms, Data Structures and Algorithms (cs.DS), cs.NE, Neural and Evolutionary Computing (cs.NE), Weisfeiler-Leman algorithm, Machine learning for graphs, Computer Science - Neural and Evolutionary Computing, stat.ML, Graph neural networks, cs.DS, 102019 Machine Learning, 102031 Theoretical computer science, equivariance
FOS: Computer and information sciences, Computer Science - Machine Learning, Machine learning for graphs; Graph neural networks; Weisfeiler-Leman algorithm; expressivity; equivariance, cs.LG, Machine Learning (stat.ML), 102019 Machine learning, expressivity, Machine Learning (cs.LG), 102031 Theoretische Informatik, Statistics - Machine Learning, Computer Science - Data Structures and Algorithms, Data Structures and Algorithms (cs.DS), cs.NE, Neural and Evolutionary Computing (cs.NE), Weisfeiler-Leman algorithm, Machine learning for graphs, Computer Science - Neural and Evolutionary Computing, stat.ML, Graph neural networks, cs.DS, 102019 Machine Learning, 102031 Theoretical computer science, equivariance
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).2 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!