Graph Machine Learning Group
Graph machine learning • Non-stationary environments • Spatiotemporal data • Reinforcement learning • Dynamical systems
About GMLG
We are a research team part of the Swiss AI Lab (IDSIA) at Università della Svizzera italiana, Lugano, Switzerland. The group is led by Prof. Cesare Alippi.
The group was previously under the ALaRI institute.
Meet our teamNews
-
Jun 2025
Two new preprints about our latest research! PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning (Zambon et al.) and Over-squashing in Spatiotemporal Graph Neural Networks (Marisca et al.). Check them out! -
Jun 2025
In collaboration with MeteoSwiss, we have released PeakWeather - a high-resolution benchmark dataset for spatiotemporal weather modeling from ground measuments. Check it out on Hugging Face! -
Jun 2025
Our paper Graph Deep Learning for Time Series Forecasting (Cini et al.) has been accepted to ACM Computing Surveys! -
May 2025
Our papers Learning Latent Graph Structures and their Uncertainty (Manenti et al.) and Relational Conformal Prediction for Correlated Time Series (Cini et al.) have been accepted at ICML 2025! -
Mar 2025
Our workshop Inductive Biases in Reinforcement Learning (IBRL) has been accepted to RLC 2025! Consider submitting your work.
Research
Our research focuses on graph machine learning, non-stationary environments, dynamical systems, and reinforcement learning.
We also apply machine learning in many diverse fields, including neuroscience, power grids, chemistry, and agriculture, among many others.
Open Source
Our group is active in open source software development and we maintain several Python libraries based on our research. Check out also the group GitHub page for code related to our papers.