Graph Machine Learning Group

Graph machine learning • Non-stationary environments • Spatiotemporal data • Reinforcement learning • Dynamical systems

The Swiss AI Lab IDSIA

Università della Svizzera italiana

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 team

News

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.

Our publications

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.

Software

Torch Spatiotemporal

A library for neural spatiotemporal data processing, with a focus on Graph Neural Networks.

Spektral

A library for building graph neural networks in Keras and Tensorflow.

CDG

A Python library for detecting changes in stationarity in sequences of graphs.

DTS

A Keras library that provides multiple deep architectures for multi-step time-series forecasting.

Datasets

PeakWeather

A high-resolution dataset of Swiss weather station measurements over 8+ years designed for spatiotemporal deep learning.

EngRad

A dataset of 5 different weather variables collected at 487 grid points in England from 2018 to 2020.

gmlg USI IDSIA Mail Github Google Scholar LinkedIn Twitter Youtube Website