Graph Neural Networks (GNNs) are a class of deep learning models that are designed to work with graph-structured data. They are an extension of traditional neural networks, which were originally developed for processing vector-based data such as images, text, or time series.
GNNs are motivated by the observation that many real-world problems can be modeled as graphs, where nodes represent entities and edges represent relationships between them.
-
[https://arxiv.org/pdf/2304.10031.pdf] Architectures of Topological Deep Learning:A Survey on Topological Neural Networks Mathilde Papillon Sophia Sanborn Mustafa Hajij Nina Miolane
-
hands on GNN github
-
The Expressive Power of GNNs page