FISMED / PEOPLE
Dionisia Naddeo
Doctoral Researcher · University of Rome Tor Vergata · CNR Institute for Complex Systems
BACKGROUND
Biography
Dionisia Naddeo is a doctoral researcher in the National PhD programme in Artificial Intelligence for Life Sciences. Her research combines graph neural networks and geometric deep learning, with applications to medical data and neuroscience. She investigates how graph structure and prediction tasks influence the choice of representation geometry. Her doctoral work involves Tor Vergata and the CNR Institute for Complex Systems. She holds a master's degree in Physics from Sapienza University of Rome, with a background in condensed matter physics.
RESEARCH & EXPERTISE
Research interests
- Graph neural networks
- Geometric deep learning
- Hyperbolic representations
- AI for neuroscience
LABORATORIES & RESEARCH
Related research
Explore related research
Connections indicate shared research topics, not authorship or project participation.
Graph neural network · Deep learning
Related laboratories
Related publications
- Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
- DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning
- Towards a predictive spatio-temporal representation of brain data
- Do We Need Curved Spaces? A Critical Look at Hyperbolic Graph Learning in Graph Classification
- Hierarchical Pooling for Sheaf Neural Networks