Francesco Di Giovanni

activity

20192022

most citedBeltrami Flow and Neural Diffusion on Graphs

15 citations · 27 across the 2 of their papers we have counts for

collaborators

4 papers

stat.ML2022★ 12 cited

Heterogeneous manifolds for curvature-aware graph embedding

Francesco Di Giovanni, Giulia Luise, Michael Bronstein

Graph embeddings, wherein the nodes of the graph are represented by points in a continuous space, are used in a broad range of Graph ML applications. The quality of such embeddings…

cs.LG2021★ 15 cited

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…

math.DG2019

Rotationally symmetric Ricci flow on $R^{n + 1}$

Francesco Di Giovanni

We study the Ricci flow on $R^{n + 1}$ , with $n \geq 2$ , starting at some complete bounded curvature rotationally symmetric metric $g_{0}$ . We first focus on the case where $…

math.DG2019

Ricci flow of warped Berger metrics on $R^{4}$

Francesco Di Giovanni

We study the Ricci flow on $R^{4}$ starting at an SU(2)-cohomogeneity 1 metric $g_{0}$ whose restriction to any hypersphere is a Berger metric. We prove that if $g_{0}$ ha…

Heterogeneous manifolds for curvature-aware graph embedding

Beltrami Flow and Neural Diffusion on Graphs

Rotationally symmetric Ricci flow on Rn+1

Ricci flow of warped Berger metrics on R4

Rotationally symmetric Ricci flow on $R^{n + 1}$

Ricci flow of warped Berger metrics on $R^{4}$