29 citations · 89 across the 8 of their papers we have counts for
5 papers · 1 filter
Relaxed Equivariance via Multitask Learning
Ahmed A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni +1
Incorporating equivariance as an inductive bias into deep learning architectures to take advantage of the data symmetry has been successful in multiple applications, such as chemis…
How does over-squashing affect the power of GNNs?
Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein +4
Graph Neural Networks (GNNs) are the state-of-the-art model for machine learning on graph-structured data. The most popular class of GNNs operate by exchanging information between…
Edge Directionality Improves Learning on Heterophilic Graphs
Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni +3
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority of today's GNN mo…
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain +2
Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph w…
Beltrami Flow and Neural Diffusion on Graphs
Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard +3
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positiona…