About Me

I am CTO of GraphSight, a Swiss startup that provides AI-powered graph-based forecasts for renewable energy systems. I recently completed my Ph.D. in the Graph Machine Learning Group at IDSIA and Università della Svizzera italiana (USI) in Lugano (Switzerland), under the supervision of Prof. Cesare Alippi. I was also part of the ELLIS Ph.D. program, jointly supervised by Prof. Alippi and Prof. Michael Bronstein. Previously, I earned my BSc (2017) and MSc (2020) in Computer Science and Engineering from Politecnico di Milano (Italy). I have been a visiting researcher at the University of Oxford with Prof. Bronstein and at UiT The Arctic University of Norway (Tromsø) with Prof. Filippo Maria Bianchi.

What I'm Doing

My research focuses on graph deep learning for irregular spatiotemporal data. I'm interested in the application of graph-based methods in problems regarding data coming from sensor networks, like imputation, filtering, and prediction of irregularly sampled observations.

You can find a list of my publications here.

Spatiotemporal data

I design machine learning models to work with data acquired across both space and time (e.g., weather, traffic).

Irregular data

I deal with data that is irregular in space (e.g., graphs) and/or time (e.g., missing values, asynchronous sampling).

Graph Neural Networks

I develop Spatiotemporal Graph Neural Networks (STGNNs) to model complex spatial dependencies in the data.

Real-world applications

I am passionate about applying my research to real-world problems, in areas like transportation and energy.

Open Source Projects

I believe in making research accessible. Whenever possible, I release my software publicly through my GitHub page. You can also find the code related to my publications on the GitHub page of Graph Machine Learning Group. Here are some of my current highlighted projects:

Torch Spatiotemporal

Torch Spatiotemporal (TSL) is a library built upon PyTorch and PyG for neural spatiotemporal data processing, with a focus on Graph Neural Networks.

Torch Geometric Pool

Torch Geometric Pool (TGP) is a library that provides a broad suite of graph pooling layers to be inserted into Graph Neural Network architectures built with PyG.

star google scholar old readthedocs.io icon Google Scholar night mode building arrow up arrow left view minus share gmlg arrow right placeholder paper plane newspaper mail heart link menu broken link dots like plus arrow down graph academic cap world sensor network interpolation usi blackboard youtube twitter instagram linkedin github facebook skype