A Novel Higher-order Weisfeiler-Lehman Graph Convolution

Clemens Damke; Vitalik Melnikov; Eyke Hüllermeier

A Novel Higher-order Weisfeiler-Lehman Graph Convolution

Machine Learning 2020-09-22 v2 Machine Learning

Authors: Clemens Damke , Vitalik Melnikov , Eyke Hüllermeier

Abstract

Current GNN architectures use a vertex neighborhood aggregation scheme, which limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman (WL) graph isomorphism test. Here, we propose a novel graph convolution operator that is based on the 2-dimensional WL test. We formally show that the resulting 2-WL-GNN architecture is more discriminative than existing GNN approaches. This theoretical result is complemented by experimental studies using synthetic and real data. On multiple common graph classification benchmarks, we demonstrate that the proposed model is competitive with state-of-the-art graph kernels and GNNs.

Keywords

graph neural network graph generation graph theory

Cite

@article{arxiv.2007.00346,
  title  = {A Novel Higher-order Weisfeiler-Lehman Graph Convolution},
  author = {Clemens Damke and Vitalik Melnikov and Eyke Hüllermeier},
  journal= {arXiv preprint arXiv:2007.00346},
  year   = {2020}
}

Related papers

View all related →