PhD Fellow - UiT The Arctic University of Norway, Department of Physics and Technology
Academic interests
Riccardo’s research lies at the intersection of Geometric Deep Learning and Model Robustness. His work focuses on developing advanced deep learning methodologies for Graph Neural Networks (GNNs), with a specific emphasis on Out-of-Distribution (OOD) detection and generalization across node, edge, and graph-level tasks. Furthermore, he is actively investigating Domain Adaptation strategies to enhance the reliability of models when deployed in unseen or shifting environments.
Background
Before joining UiT as a Ph.D. Fellow, Riccardo earned both his Bachelor’s and Master’s degrees (110/110 cum laude) in Computer Science Engineering from Politecnico di Milano. During his Master’s, he specialized in the adaptation of Foundation Models, developing a thesis on the cross-domain application of the Segment Anything Model (SAM) to Synthetic Aperture Radar (SAR) imagery for automated avalanche segmentation.
PhD project
Out Of Distribution (OOD) detection applied to graphs
Supervisors
- Associate Professor Veronica Lachi, UiT The Arctic University of Norway, Department of Physics and Technology