I am a postdoctoral researcher at EPFL, working with the LTS2 and LPDI laboratories.

I research graph neural networks and their applications to dynamical systems and computational biology, specifically for protein design. I am also the main developer of Spektral, a library for graph deep learning in TensorFlow/Keras.

I obtained my PhD at IDSIA, as part of the GML group. I hold an MSc in Computer Science and Engineering with honors from Politecnico di Milano.

In my free time, I co-host and manage Smarter Podcast, a live streaming podcast in Italian in which we interview AI researchers from academia and industry.


This is a summary of my active projects. You can find a complete list of publications here (including links to code) and a summary of my academic activity here.

Graph Neural Networks.
My core research is on graph neural networks and their applications. I have published several papers that introduced state-of-the-art methods for graph representation learning and graph pooling.

Protein design.
I have recently joined EPFL to work on geometric deep learning methods for protein design. Stay tuned for a lot of exciting and impactful research!

Spektral is an open-source Python library that provides a simple but flexible framework for creating graph neural networks in TensorFlow and Keras.
I recently released version 1.0 of the library, which brings several new features and improvements.

I am always looking for new and exciting research ideas, so get in touch with me if you want to work together.
A list of open projects for students is available here.


I had the absolute pleasure of chatting about cellular automata, emergence, life, graphs, and much more with the amazing Tim and Keith of Machine Learning Street Talk!

In collaboration with part of the team that I mentored at LOGML 2021, we have released a preprint on unsupervised embedding of heterophilous graphs.

I have become a member of the ELLIS Society, one of the leading non-profit organizations for promoting European AI.

I am co-organizing a special session on Deep Learning for Graphs (DL4G) at WCCI 2022. Read the call for papers here.

I have successfully defended my PhD dissertation!

Our paper "Learning graph cellular automata" will appear at NeurIPS 2021.

Our paper "Understanding pooling in graph neural networks" is out on arXiv.

The paper from my collaboration with Menten AI, "XENet: using a new graph convolution to accelerate the timeline for protein design on quantum computers", was published in PLOS Computational Biology.