Adventures in geometric deep learning

PI Stories 2022
6 June 2022
Start time 
10:00 am
Polo Ferrari 1 - Via Sommarive 5, Povo (Trento)
Room A203
Doctoral Programme in Information Engineering and Computer Science (IECS)
Target audience: 
University community
Free – Registration required
Registration deadline: 
5 June 2022, 23:59
Contact person: 
prof. Elisa Ricci
Emanuele Rodolà (Università la Sapienza, Roma)


In this talk I will present several recent directions of research in the areas of machine learning and applied AI, the so called "geometric deep learning" subfield; common to these topics are the notions of geometry and structure.
I'll start by showing how data-driven methods can serve as efficient and robust drop-in replacements for classical axiomatic constructions, even when learning is not strictly necessary, for typical tasks of geometry and signal processing; in turn, I'll show how geometry itself can serve as a valid proxy for better machine learning pipelines. I'll then explore some preliminary steps toward the application of geometric deep learning in other fundamental disciplines, such as mathematical physics and structural biology, and conclude with an overview of some work in progress in our lab as well as some wishful thinking on future perspectives.

About the speaker

Emanuele Rodolà is Full Professor in Computer Science at Sapienza University of Rome, where he leads the GLADIA group of Geometric Learning & AI funded by an ERC Starting Grant, a Google Research Award, and a PRIN grant.
Previously, he was a postdoc at USI Lugano, TU Munich, and the University of Tokyo. He received a number of awards, including several best paper prizes, has been serving as area chair and in the program committees of the top rated conferences in computer vision and graphics (CVPR, ICCV, ECCV, SGP, EG, etc.), co-founded and chaired the successful workshop on Geometry Meets Deep Learning (co-located with ECCV/ICCV, 2016–2019), gave tutorials and short courses in multiple occasions at EUROGRAPHICS, ECCV, SGP, SIGGRAPH, and was recognized (10 times) as IEEE Outstanding Reviewer at CVPR/ICCV/ECCV. He spent visiting periods at Stanford, Harvard, Ecole polytechnique and Technion among others.
His research interests include geometric deep learning, geometry processing, natural language and sound processing and interactions thereof, and has published around 100 papers on these topics.

Next story on 20 October at 1 pmReverse-engineering Drosophila action selection and movement control by Pavan Ramdya, EPFL - Ecole Polytechnique Federale de Lausanne

Pi Stories: A series of seminars aimed at providing the opportunity to the PhD students to learn the success stories of some of the most talented researchers in the world. Each speaker will present a research project he/she led as a principal investigator. The presentation will cover the scientific scope of the project and the most important results the project achieved. The speakers will also share their own experience of turning a research idea into a successful project winning a competitive grant.