Topological deep learning (TDL) is a rapidly evolving field that uses topological features to
understand and design deep learning models. This paper posits that TDL may complement …

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to
understand and design deep learning models. This paper posits that TDL is the new frontier …

Graph neural networks (GNNs) have demonstrated significant promise in modelling
relational data and have been widely applied in various fields of interest. The key …

Graph-based message-passing neural networks (MPNNs) have achieved remarkable
success in both node and graph-level learning tasks. However, several identified problems …

Learning representations for structured data with certain geometries (observed or
unobserved) is a fundamental challenge, wherein message passing neural networks …

Real-world data generation often involves certain geometries (eg, graphs) that induce
instance-level interdependence. This characteristic makes the generalization of learning …