Whether you're new to the field or an experienced researcher, this meetup offers great opportunities for networking, learning, and discussing the latest advances in graph-based machine learning. Full information (external link)
Registration: before Wednesday 11 February 2026.
Tentative Schedule
Day 1
08:45 Registration. Morning talk + PhD Kitchen
09:00 Keynote 1 : Sabrina Gaito
Abstract: TBA
10:00 Coffee Break
10:15 Coding session 1: Veronica Lachi
Title: Introduction to PyTorch Geometric
This coding session will cover the basics of PyTorch Geometric, including data handling, model building, and training of graph neural networks. Students will get hands-on experience with key concepts and tools.
11:30 Coffee Break
11:45 Coding session 2: Carlo Abate
Title: Advanced PyTorch Geometric with Torch Geometric Pool
This coding session will cover advanced topics in PyTorch Geometric with the Torch Geometric Pool library, including pooling techniques and graph coarsening. Participants will learn how to implement and utilize these methods effectively to improve graph neural network performance.
13:00 Lunch break
14:00 Afternoon talk + poster session
14:15 Keynote 2: Davide Bacciu
15:15 Break
15:30 Poster session + Pizza
17:00 End of day 1
20:00 Meetup social event in the city center
Day 2
08:45 Welcome back!
09:00 Tutorial (part 1): Andrea Cini
Title: Graph Deep Learning for Time Series Forecasting
Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. This tutorial will explore these methods in depth, providing practical examples and insights.
11:00 Coffee Break
10:45 Tutorial (part 2): Andrea Cini
12:30 End of Meetup
Topics of Interest (non-exhaustive list)
- Graph Neural Networks (GNNs)
- Graph representation learning
- Graph pooling and coarsening
- Applications of GNNs in various domains
- Theoretical aspects of graph learning
- Graph signal processing
- Network science and analysis
- Geometric deep learning
- Call for Contributions
We welcome contributions in the form of posters! If you're interested in presenting your work, please reach out to us at roberto.neglia@uit.no with an abstract of your poster by February 11th, 2026.
Contact and information
For questions or more information about the event, please contact us at roberto.neglia@uit.no