English

Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm

Machine Learning 2021-04-06 v1

Abstract

In recent years, Graph Neural Network (GNN) has bloomly progressed for its power in processing graph-based data. Most GNNs follow a message passing scheme, and their expressive power is mathematically limited by the discriminative ability of the Weisfeiler-Lehman (WL) test. Following Tinhofer's research on compact graphs, we propose a variation of the message passing scheme, called the Weisfeiler-Lehman-Tinhofer GNN (WLT-GNN), that theoretically breaks through the limitation of the WL test. In addition, we conduct comparative experiments and ablation studies on several well-known datasets. The results show that the proposed methods have comparable performances and better expressive power on these datasets.

Keywords

Cite

@article{arxiv.2104.01848,
  title  = {Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm},
  author = {Alan J. X. Guo and Qing-Hu Hou and Ou Wu},
  journal= {arXiv preprint arXiv:2104.01848},
  year   = {2021}
}
R2 v1 2026-06-24T00:51:08.068Z