Topological Graph Neural Networks
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.
Cite
Text
Horn et al. "Topological Graph Neural Networks." International Conference on Learning Representations, 2022.Markdown
[Horn et al. "Topological Graph Neural Networks." International Conference on Learning Representations, 2022.](https://mlanthology.org/iclr/2022/horn2022iclr-topological/)BibTeX
@inproceedings{horn2022iclr-topological,
title = {{Topological Graph Neural Networks}},
author = {Horn, Max and De Brouwer, Edward and Moor, Michael and Moreau, Yves and Rieck, Bastian and Borgwardt, Karsten},
booktitle = {International Conference on Learning Representations},
year = {2022},
url = {https://mlanthology.org/iclr/2022/horn2022iclr-topological/}
}