About me

Praise the sun! I am currently at Twitter Cortex as a postdoctoral ML Researcher working on Geometric Deep Learning and more specifically Graph Neural Networks with Michael Bronstein. I finished my PhD in Mathematics at UCL with a thesis on analysis of singularity formation of rotationally symmetric Ricci Flows. I am now interested in investigating Deep Learning through the lens of Differential Geometry and Physics, with emphasis on graph structured data and treating time as a continuous variable.

My current lines of research regard: (i) leveraging the graph structure via local tools as curvature to investigate how information flows inside a Message Passing Neural Network - our first step in this direction got an ICLR honorable mention! - and propose principled rewiring approaches inspired by geometric flows. (ii) Study Graph Neural Networks as multi-particles dynamics - our recent work explains how the common “channel-mixing” module can be interpreted as a pairwise potential and how by interacting with the graph Laplacian spectrum it learns to generate attractive or repulsive forces via its positive and neagtive eigenvalues respectively.

Contact: francesco.dgv94 (at) gmail (dot) com

News

2022

  • August: I will give a long talk at the Hammers and Nails 2022 Workshop in Tel Aviv
  • July: I will be a lecturer at the First Italian School in Geometric Deep Learning
  • July: I have been a mentor at the LOGML22 - our project is about graph-rewiring using geometric exploration policies
  • June: I have reviewed for NeurIPS 2022
  • May: I have coauthored a blogpost with Michael Bronstein and Cristing Bodnar on a recent about cellular sheaf theory for tackling heterophily in GNNs
  • April: Our work on understanding over-squashing in GNNs through graph curvature has got an Outstanding Paper Honorable Mention at ICLR 2022!
  • April: Aleksa Gordić made a great video about our paper on bottlenecks and over-squashing in GNNs. This is highly recommended to anyone interested in understanding our work in quite some detail!
  • March: I gave a talk at the Dagsthul seminar Graph Embeddings: Theory meets Practice
  • January: I have been invited to write my opinion on future perspetives of GNNs in a blogpost authored by Michael Bronstein and Petar Veličković, featuring many prominent researchers in the field.