Francesco Di Giovanni

29 papers A* 9Journal 18Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition.
ICML
Nian Liu, Xiaoxin He, Thomas Laurent, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson
2025 J jnl
MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models.
CoRR
Kacper Kapusniak, Cristian Gabellini, Michael M. Bronstein, Prudencio Tossou, Francesco Di Giovanni
2025 A* conf
Understanding Virtual Nodes: Oversquashing and Node Heterogeneity.
ICLR
Joshua Southern, Francesco Di Giovanni, Michael M. Bronstein, Johannes F. Lutzeyer
2024 J jnl
Advancing Graph Convolutional Networks via General Spectral Wavelets.
CoRR
Nian Liu, Xiaoxin He, Thomas Laurent, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson
2024 J jnl
How does over-squashing affect the power of GNNs?
Trans. Mach. Learn. Res.
Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein, Andreea Deac, Marc Lackenby, Siddhartha Mishra, Petar Velickovic
2024 A* conf
Locality-Aware Graph Rewiring in GNNs.
ICLR
Federico Barbero, Ameya Velingker, Amin Saberi, Michael M. Bronstein, Francesco Di Giovanni
2024 A* conf
Metric Flow Matching for Smooth Interpolations on the Data Manifold.
NeurIPS
Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael M. Bronstein, Avishek Joey Bose, Francesco Di Giovanni
2024 J jnl
Metric Flow Matching for Smooth Interpolations on the Data Manifold.
CoRR
Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael M. Bronstein, Avishek Joey Bose, Francesco Di Giovanni
2024 J jnl
Relaxed Equivariance via Multitask Learning.
CoRR
Ahmed A. A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni, Michael M. Bronstein
2024 J jnl
Understanding Virtual Nodes: Oversmoothing, Oversquashing, and Node Heterogeneity.
CoRR
Joshua Southern, Francesco Di Giovanni, Michael M. Bronstein, Johannes F. Lutzeyer
2023 — conf
Can strong structural encoding reduce the importance of Message Passing?
TAG-ML
Floor Eijkelboom, Erik J. Bekkers, Michael M. Bronstein, Francesco Di Giovanni
2023 J jnl
Can strong structural encoding reduce the importance of Message Passing?
CoRR
Floor Eijkelboom, Erik J. Bekkers, Michael M. Bronstein, Francesco Di Giovanni
2023 A* conf
DRew: Dynamically Rewired Message Passing with Delay.
ICML
Benjamin Gutteridge, Xiaowen Dong, Michael M. Bronstein, Francesco Di Giovanni
2023 J jnl
DRew: Dynamically Rewired Message Passing with Delay.
CoRR
Benjamin Gutteridge, Xiaowen Dong, Michael M. Bronstein, Francesco Di Giovanni
2023 — conf
Edge Directionality Improves Learning on Heterophilic Graphs.
LoG
Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni, Fabrizio Frasca, Stephan Günnemann, Michael M. Bronstein
2023 J jnl
Edge Directionality Improves Learning on Heterophilic Graphs.
CoRR
Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni, Fabrizio Frasca, Stephan Günnemann, Michael M. Bronstein
2023 J jnl
How does over-squashing affect the power of GNNs?
CoRR
Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein, Andreea Deac, Marc Lackenby, Siddhartha Mishra, Petar Velickovic
2023 J jnl
Locality-Aware Graph-Rewiring in GNNs.
CoRR
Federico Barbero, Ameya Velingker, Amin Saberi, Michael M. Bronstein, Francesco Di Giovanni
2023 A* conf
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology.
ICML
Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero, Giulia Luise, Pietro Lio, Michael M. Bronstein
2023 J jnl
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology.
CoRR
Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero, Giulia Luise, Pietro Lio', Michael M. Bronstein
2023 J jnl
Understanding convolution on graphs via energies.
Trans. Mach. Learn. Res.
Francesco Di Giovanni, James Rowbottom, Benjamin Paul Chamberlain, Thomas Markovich, Michael M. Bronstein
2022 J jnl
Graph Neural Networks as Gradient Flows.
CoRR
Francesco Di Giovanni, James Rowbottom, Benjamin Paul Chamberlain, Thomas Markovich, Michael M. Bronstein
2022 J jnl
Heterogeneous manifolds for curvature-aware graph embedding.
CoRR
Francesco Di Giovanni, Giulia Luise, Michael M. Bronstein
2022 A* conf
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs.
NeurIPS
Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Lió, Michael M. Bronstein
2022 J jnl
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs.
CoRR
Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Liò, Michael M. Bronstein
2022 A* conf
Understanding over-squashing and bottlenecks on graphs via curvature.
ICLR
Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein
2021 A* conf
Beltrami Flow and Neural Diffusion on Graphs.
NeurIPS
Ben Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni, Xiaowen Dong, Michael M. Bronstein
2021 J jnl
Beltrami Flow and Neural Diffusion on Graphs.
CoRR
Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni, Xiaowen Dong, Michael M. Bronstein
2021 J jnl
Understanding over-squashing and bottlenecks on graphs via curvature.
CoRR
Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein