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.
Meet our teamNews
-
May 2024
Two papers accepted at ICML 2024! Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting (Cini et al.) and Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (Marisca et al.). -
Dec 2023
Submit by Jan. 15 to our special sessions Deep Learning for Graphs at IEEE WCCI 2024 in Yokohama, Japan (Jun. 30-Jul. 5). -
Sep 2023
Our paper Taming Local Effects in Graph-based Spatiotemporal Forecasting (Cini et al.) has been accepted at NeurIPS 2023! -
Aug 2023
Our paper Sparse Graph Learning from Spatiotemporal Time Series (Cini et al.) has been published in JMLR! -
May 2023
We uploaded 8 new preprints about our latest research! Check them out: learning graph structures from data [1,2,3], state-space modeling [4,5], spatio-temporal time-series processing [6,7], generative models [8].
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.
The development of Spektral and CDG was supported by project ALPSFORT (200021 172671) of the Swiss National Science Foundation.