Francesco Ferrini

Hi there 🌱

I am Francesco Ferrini, a researcher in Artificial Intelligence and Machine Learning. I recently completed my Ph.D. in Artificial Intelligence and Machine Learning at the Structured Machine Learning Group, University of Trento, Italy, under the supervision of Andrea Passerini (University of Trento) and Manfred Jaeger (Aalborg University, Denmark).

My research focuses on Graph Neural Networks (GNNs) and relational learning, with particular interest in:

• Heterogeneous and multi-relational graphs — meta-path learning, self-explainable models, relational deep learning on databases.
• Link prediction — structural link representation, expressiveness of GNNs at the link level, shortest-path-based methods.
• Learning with imperfect data — GNNs with missing node features, realistic missingness mechanisms, robust evaluation.

During my Ph.D., I also carried out a research period in Japan at the National Institute of Advanced Industrial Science and Technology (AIST), where I worked with academic and industrial researchers on graph-based learning in applied and interdisciplinary settings.

Prior to my doctoral studies, I obtained a Master's degree in Artificial Intelligence Systems. During this period, I worked on several projects spanning Machine Learning, Deep Learning, Computer Vision, and Natural Language Processing. I also interned at Aalborg University in Denmark, where I began my Master's thesis research on meta-path learning for Graph Neural Networks in heterogeneous graphs.

Outside of research, I enjoy practicing sports — especially calisthenics and tennis — and playing chess.

Feel free to explore my publications, talks, blog, and projects. If you are interested in collaboration, have a research idea, or would simply like to discuss science and technology, do not hesitate to get in touch.

• Contact me at francescoferrini1997@gmail.com