Learning on Graphs Italian Meetup
Italian Meetup - Pisa 🇮🇹
June 9-11, 2026 📅
Welcome to the official website of the 2025 Learning on Graphs (LoG) Italian Meetup, hosted in the beautiful city of Pisa! This event is a local branch of the main LoG conference, which brings together researchers, practitioners, and enthusiasts in the field of machine learning on graphs and geometry.
The event is open to everybody as a local branch of the main conference, providing an environment for researchers in this field to convene and foster social connections. A registration is required to secure your spot, and it includes the lunch and coffee breaks.
The meetup will host a poster session where researchers and practitioners can present their latest findings and innovations on topics broadly related to learning on graphs and geometry. A selected subset of posters will also be invited to give an oral presentation. Check out the Call for Posters and Registration sections below for more information.
📍 Event Details
Date
June 9-11, 2026
📢 Call for Posters
- Poster abstracts must be prepared using the official LoG meetup LaTeX style files. Poster abstracts must not exceed 500 words (references excluded).
- All submissions will be reviewed by the local organizing committee. A selected subset of posters will also be invited to give an oral presentation.
📅 Important Dates
Extended Submission Deadline: May 10, 2026Final Decision: May 17, 2026Registration Deadline: May 22, 2026
🎯 Subject Areas
The meetup follows the focus of the Learning on Graphs Conference. A non-exhaustive list of subject areas can be found in the official LoG call for papers.
🎟️ Registration
Registration is now open and free of charge! Secure your spot for the LoG Italian Meetup in Pisa. Registration includes lunch and coffee breaks.
📅 Program Schedule
| June 2026 | |||
|---|---|---|---|
| Time | Tue 9 | Wed 10 | Thu 11 |
| 9.30 - 10.00 | Keynote Luca Cosmo |
Keynote Alessandro Sperduti |
|
| 10.00 - 10.30 | |||
| 10.30 - 11.00 | Coffee Break | Coffee Break | |
| 11.00 - 11.30 | Samuel Cognolato Diffusion Models for Autoregressive, Incremental, and 3D Graph Generation |
Panel Discussion Monica Bianchini, Federico Errica, Alessandro Sperduti |
|
| 11.30 - 12.00 | Alessandro Trenta Long-range Propagation through the Graph Wave Equation |
||
| 12.00 - 12.30 | Matteo Ninniri Graph Diffusion that can Insert and Delete |
||
| 12.30 - 13.00 | Lunch | Closing Remarks | |
| 13.00 - 14.00 | Registration | ||
| 14.00 - 14.30 | Welcome Talk | Poster Session | |
| 14.30 - 15.00 | Keynote Veronica Lachi |
||
| 15.00 - 15.30 | |||
| 15.30 - 16.00 | Coffee Break | Coffee Break | |
| 16.00 - 16.30 | Matteo Baldan Neural operator on multi-resolution scale data for virtual heart modeling |
Poster Session | |
| 16.30 - 17.00 | Ivan Marisca Over-squashing in Spatiotemporal Graph Neural Networks |
||
| 17.00 - 17.30 | Stefano Carotti Graph Hierarchical Recurrence for Long-Range Generalization |
||
🖼️ Poster Session 1
- – Hierarchical Graph-of-Graphs Learning for Multimodal Alzheimer’s Disease Staging and Progression Modelling
- – Analysis of Dirichlet Energies as Over-smoothing Measures
- – SPECTRA: Modeling Genetic Perturbations via Graph Signal Propagation over Gene Regulatory Networks
- – Graph Hierarchical Recurrence for Long-Range Generalization
- – Diffusion Models for Autoregressive, Incremental, and 3D Graph Generation
- – Adaptive Memory Retention in Dynamic Graphs
- – Time-Expanded Graph Learning for Multi-Agent Temporal Interaction Modeling with Counterfactual Interventions
- – Temporal graph learning for biological systems: forecasting gene interactions under latent time
- – The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
- – Oversmoothing, “Oversquashing”, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
- – On the Rademacher Complexity of Graph Neural Networks: Unifying Expressivity and Geometry
- – Bridging Theory and Practice in Link Representation with Graph Neural Networks
- – Game-Theoretic Competitive Message Passing for Graph Neural Networks
- – GraphVAEBM: Molecular Graph Generation Combining Variational Autoencoders and Energy-Based Models
- – Hierarchical Sheaf Neural Networks
- – Dynamic Graph Clustering with Graph Neural Networks
- – Long-range Propagation through the Graph Wave Equation
- – PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning
🖼️ Poster Session 2
- – GRAVE: a GRAphon–based Variational autoEncoder
- – Neural operator on multi-resolution scale data for virtual heart modeling
- – Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
- – Discovering Generalizable Governing Equations for Graph Dynamical Systems with Interpretable Neural Networks
- – PANDA: Prior-guided Attentional Dual-path Architecture
- – GraphNeuralRAG: Filling the Recall Gap in Multi-Hop Question Answering
- – The role of network dynamics in drug response prediction
- – UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
- – Early-Exit Graph Neural Networks for Link Prediction
- – Asocial networks and their connection problems
- – Over-squashing in Spatiotemporal Graph Neural Networks
- – Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
- – Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry–Task Alignment
- – Graph Diffusion that can Insert and Delete
- – OpenGraphXAI: A library for automatic graph XAI benchmark construction
- – AI Research Support Systems and Tools: A Survey
- – Leveraging Single-Sample Networks for Predictive Modelling of Longitudinal Clinical Data
- – RIM4G: Graph Learning Beyond von Neumann Computing Architectures
👥 Organizers
🤝 Sponsor
