Graph Neural Networks via Sheaves
Abstract: The multitude of applications where data is attached to spaces with non-Euclidean structure has driven the rise of the field of Geometric Deep Learning (GDL). Nonetheless, from many points of view, geometry does not always provide the right level of abstraction to study all the spaces that commonly emerge in such settings. For instance, graphs, by far the most prevalent type of space in GDL, do not even have a geometrical structure in the strict sense. In this talk, I will explore how we can take a (more general) topological perspective of the field with a focus on understanding and developing new Graph Neural Network models.
Cristian Bodnar, Senior Researcher @ Microsoft Research. Previously @ Google Brain, Google X, Twitter Cortex
Cristian is a Senior Researcher at Microsoft Research in the AI4Science team where he is working at intersection of deep learning and partial differential equations (PDEs). On the ML side, his research spans a range of topics such as geometric & topological deep learning, graph neural networks and neural differential equations.
Previously, Cristian finished his PhD at the University of Cambridge, supervised by Prof Pietro Liò and supported by a Microsoft Research PhD Fellowship (2021). Cristian also spent significant time in industry as a research intern at Microsoft Research (2022), Twitter Cortex (2021), Google Brain (2020), and as an AI Resident at Google X (2019). In 2019, he graduated with distinction the MPhil in Advanced Computer Science at Cambridge with a Best MPhil Student Award.
Agenda:
14:30 - Registration and Arrival
15:00 - Welcome and introductions
15:10 - Cristian Bodnar, Senior Researcher at Microsoft Research (Graph Neural Networks / Geometric deep learning.)
15:45 - Q&A
16:00 - Networking
16:30 - Event close
