On the 30th November 2023, the Institute for Data Science and AI welcomed Cristian Bodnar, Senior Researcher at Microsoft Research, to present his talk on Graph Neural Networks via Sheaves.
The seminar was kicked off by Magnus Rattray, Professor in Computational & Systems Biology and Director of the Institute for Data Science & Artificial Intelligence at The University of Manchester. After a short introduction by Professor Rattray, Cristian Bodnar began his presentation.
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 was an undergraduate student at The University of Manchester after which he moved to the University of Cambridge to finish his PhD. At Cambridge, he was supervised by Professor Pietro Liò and supported by a Microsoft Research PhD Fellowship. In 2019, he graduated with distinction the MPhil in Advanced Computer Science at Cambridge with a Best MPhil Student Award. 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).
Cristian's talk focused on the multitude of applications where data is attached to spaces with non-Euclidean structure, which has driven the rise of the field of Geometric Deep Learning (GDL). However, Cristian argues that, 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. During the talk, Cristian explored how we can take a (more general) topological perspective of the field with a focus on understanding and developing new Graph Neural Network models.
After an insightful seminar, a Q&A session soon followed, in which attendees could ask questions to the speaker. Following this, Professor Rattray brought the event to a close.
If you missed this event, you can watch it back here:
If you are interested in joining future events you can sign up for our IDSAI newsletter and follow our Twitter account @idsai_uom. Delivered by The University of Manchester's wider Digital Futures network, the Institute for Data Science and Artificial Intelligence is highly interdisciplinary and delivers the University's Data Science strategy - connect with us and keep in touch: