Topological Graph Neural Networks

Author name not available (Why is that?)

Publication date: 15 February 2021

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.

Has companion code repository: https://github.com/borgwardtlab/togl

This page was built for publication: Topological Graph Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6360700)