Publications

Preprint
Wasserstein Hypergraph Neural Network
I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Pietro Liò

Preprint
Sheaves Reloaded: A Directional Awakening
Stefano Fiorini, Hakan Aktas, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Stefano Coniglio, Pietro Morerio, Alessio Del Bue, Pietro Liò

ICML 25
SPHINX: Structural Prediction using Hypergraph Inference Network
I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Pietro Liò
International Conference on Machine Learning 2025

Preprint
Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts
Shiye Su, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Lucie Charlotte Magister, Pietro Liò

Preprint
Heterogeneous sheaf neural networks
Luke Braithwaite, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Pietro Liò
ICML 2024 Workshop, GRaM: Geometry-grounded Representation Learning and Generative Modeling

GRaM 24
Joint Diffusion Processes as an Inductive Bias in Sheaf Neural Networks
Ferran Hernandez Caralt, Guillermo Bernárdez Gil, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Pietro Liò, Eduard Alarcón Cot
ICML 2024 Workshop, GRaM: Geometry-grounded Representation Learning and Generative Modeling

NeurIPS 23
Sheaf Hypergraph Networks
I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟, Giulia Cassarà, Fabrizio Silvestri, Pietro Liò
Annual Conference on Neural Information Processing Systems 2023

NeurIPS 21
Dynamic Regions Graph Neural Networks for Spatio-Temporal Reasoning
I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟*, Andrei Nicolicioiu*, Marius Leordeanu
Annual Conference on Neural Information Processing Systems 2021

NeurIPS 19
Recurrent Space-time Graph Neural Networks
Andrei Nicolicioiu*, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟*, Marius Leordeanu
Annual Conference on Neural Information Processing Systems 2019

Preprint
Effective Receptive Field of Graph Neural Networks
Andrei Nicolicioiu*, I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟*

BMVC 2018
Mining for meaning: from vision to language through multiple networks consensus
I͟u͟l͟i͟a͟ ͟D͟u͟t͟a͟*, Andrei Nicolicioiu*, Vlad Bogolin, Marius Leordeanu
The British Machine Vision Conference 2018