Topological Graph Neural Networks
Max Horn, Edward De Brouwer, Michael Moor, Yves Moreau, Bastian Rieck, Karsten Borgwardt
Abstract
Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures such as cycles. We present TOGL, a novel layer that incorporates global topological information of a graph using persistent homology. TOGL can be easily integrated into any type of GNN and is strictly more expressive (in terms the Weisfeiler–Lehman graph isomorphism test) than message-passing GNNs. Augmenting GNNs with TOGL leads to improved predictive performance for graph and node classification tasks, both on synthetic data sets, which can be classified by humans using their topology but not by ordinary GNNs, and on real-world data.
BibTeX
@inproceedings{
horn2022topological,
title={Topological Graph Neural Networks},
author={Max Horn and Edward De Brouwer and Michael Moor and Yves Moreau and Bastian Rieck and Karsten Borgwardt},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=oxxUMeFwEHd}
}