Francesco Di Giovanni

Understanding over-squashing and bottlenecks on graphs via curvature

Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain et al. · arXiv (Cornell University) · 2021 · 34 citations · Full text

Graph Sparsity, Engineering, Machine Learning +17

On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology

Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero et al. · arXiv (Cornell University) · 2023 · 31 citations · Full text

Artificial Intelligence, Graph Sparsity, Engineering +19

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain et al. · arXiv (Cornell University) · 2022 · 29 citations · Full text

Neural Sheaf Diffusion, Network Science, Graph Theory +15

Edge Directionality Improves Learning on Heterophilic Graphs

Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni et al. · arXiv (Cornell University) · 2023 · 22 citations · Full text

Geometric Learning, Graph Neural Networks, Network Science +13

Beltrami Flow and Neural Diffusion on Graphs

Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard et al. · arXiv (Cornell University) · 2021 · 15 citations · Full text

Geometric Learning, Graph Representation Learning, Machine Learning +21