<aside> 👋 Hello world!

I am a PhD student in the AMLab, at University of Amsterdam, supervised by Prof. Erik Bekkers and Prof. Rita Fioresi. I am working on Geometric Deep Learning topics as part of the CaLIForNIA (Cartan and differential geometry, Lie theory, quantum groups and non commutative geometry For novel and Innovative Applications to quantum algorithms and geometric deep learning) Marie Skłodowska-Curie Doctoral Network.

Previously, I was a research intern at EPFL in the Signal Processing Laboratory 4, supervised by Prof. Pascal Frossard and Prof. Laura Toni, working on discrete diffusion models for graph generation. Before EPFL, I was a research intern at KAIST in the Vision and Learning Laboratory, supervised by Prof. Seunghoon Hong and Jinwoo Kim, working on deep learning models for graph data based on random walks.

****I wrote my MSc Thesis on Sheaf Neural Networks in the Computer Laboratory at the University of Cambridge under the supervision of Prof. Pietro Liò and Prof. Andrea Passerini.

I completed my MSc in Artificial Intelligence Systems at University of Trento, and my BSc in Mathematics at University of Milan.

</aside>

📧 Email

🐦 X

🔗 LinkedIn

👾 Github

👩🏼‍💻 Google Scholar

Research

ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain Guillermo Bernárdez et al. Preprint (2024)

Sheaf Diffusion Goes Nonlinear: Enhancing GNNs with Adaptive Sheaf Laplacians Olga Zaghen, Antonio Longa, Steve Azzolin, Lev Telyatnikov, Andrea Passerini, Pietro Liò ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling (2024)

Revisiting Random Walks for Learning on Graphs Jinwoo Kim, Olga Zaghen, Ayhan Suleymanzade, Youngmin Ryou, Seunghoon Hong ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling (2024)

Nonlinear Sheaf Diffusion in Graph Neural Networks Olga Zaghen Preprint (MSc Thesis) (2024)

TopoX: A Suite of Python Packages for Machine Learning on Topological Domains Mustafa Hajij et al. Preprint (2024)

Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design Lev Telyatnikov, Maria Sofia Bucarelli, Guillermo Bernardez, Olga Zaghen, Simone Scardapane, Pietro Liò Preprint (2023) **

ICML 2023 Topological Deep Learning Challenge: Design and Results Mathilde Papillon et al. *Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML)* (2023)


Awards

🏆 Part of the winning team for the Hypergraph, Simplicial and Cellular domains in the ICML 2023 TopoModelX Challenge


Invited Talks

🗣 Nonlinear Sheaf Diffusion in Graph Neural Networks @ Geometry and Machine Learning Calista Workshop in Scalea, Italy