A Survey on The Expressive Power of Graph Neural Networks

Ryoma Sato

A Survey on The Expressive Power of Graph Neural Networks

Machine Learning 2020-10-19 v4 Machine Learning

Authors: Ryoma Sato

Abstract

Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs.

Keywords

graph neural networks expressive power provably powerful variants graph learning theoretical limitations

Cite

@article{arxiv.2003.04078,
  title  = {A Survey on The Expressive Power of Graph Neural Networks},
  author = {Ryoma Sato},
  journal= {arXiv preprint arXiv:2003.04078},
  year   = {2020}
}

Comments

42 pages

Related papers

View all related →