Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
Published in International Conference on Learning Representations (ICLR), 2025
We develop a GNN architecture capable of Long-range propagation exploiting the Hamiltonian formulation of Physical Dynamics
Recommended citation: Heilig S.*, Gravina A.*, Trenta A., Gallicchio C., Bacciu D., (2025). "Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks." International Conference on Learning Representations (ICLR).
Download Paper | Download Bibtex
SONAR: Long-Range Graph Propagation through Information Waves
Published in Neural Information Processing Systems (NeurIPS), 2025
We design a novel GNN model capable of long-range propagation using the wave equation on graphs
Recommended citation: Trenta A.*, Gravina A.*, Bacciu D., (2025). "SONAR: Long-Range Graph Propagation through Information Waves" Neural Information Processing Systems (NeurIPS).
Download Paper | Download Bibtex
Learning and Transferring Physical Models Trhough Derivatives
Published in Transactions on Machine Learning Research (TMLR), 2026
We introduce DERL, a supervised approach based on partial derivatives that is able to learn physical systems and to transfer physical knowledge across models.
Recommended citation: Trenta A., Cossu A., Bacciu D., (2026). "Learning and Transferring Physical Models through Derivatives" Transactions on Machine Learning Research (TMLR).
Download Paper | Download Slides | Download Bibtex
ComPhy: Composing Physical Models with end-to-end Alignment
Published in International Conference on Learning Representations (ICLR), 2026
We introduce ComPhy, a multi-module approach to learn systems of PDEs by assigning one equation to each module. An alignment mechanism ensures the networks share information to solve the system together.
Recommended citation: Trenta A., Cossu A., Bacciu D., (2026). "ComPhy: Composing Physical Models with end-to-end Alignment" International Conference on Learning Representations (ICLR).
Download Paper | Download Bibtex
Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
Published in International Conference on Learning Representations (ICLR), 2026
We propose a novel Graph Neural Simulator that preserves information during propagation, enabling it to model complex physical dynamical systems with long-range dependencies.
Recommended citation: Hoang T., Trenta A.*, Gravina A., Freymuth N., Becker P., Bacciu D., Neumann G., (2026). "Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics" International Conference on Learning Representations (ICLR).
Download Paper | Download Bibtex
talks
Long-range Propagation through the Graph Wave Equation
Published:
This talk, which was selected for an Oral Presentation at the LoG Italian Meetup 2026, shows how the wave equation on Graphs can be used to enhance the Long-Range capabilities of Message Passing Neural Networks on Graphs. Starting from the physical intuitions, the presentation gradually develops the full model and its extension from static graphs to dynamic ones. Taken from the work with Alessio Gravina at University of Pisa and other colleagues. The presentation is available here!