BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Graph Neural Networks through the lens of algebraic topology\, dif
 ferential geometry\, and PDEs - Professor Michael Bronstein - Department o
 f Computer Science\, University of Oxford
DTSTART:20220309T150500Z
DTEND:20220309T155500Z
UID:TALK169952@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:The message-passing paradigm has been the “battle horse” o
 f deep learning on graphs for several years\, making graph neural networks
  a big success in a wide range of applications\, from particle physics to 
 protein design. From a theoretical viewpoint\, it established the link to 
 the Weisfeiler-Lehman hierarchy\, allowing to analyse the expressive power
  of GNNs. I argue that the very “graph-centric” mindset of current gra
 ph deep learning schemes may hinder future progress in the field. As an al
 ternative\, I propose physics-inspired “continuous” learning models th
 at open up a new trove of tools from the fields of differential geometry\,
  algebraic topology\, and differential equations so far largely unexplored
  in graph ML.\n\nWe are asking those attending in person to please take a 
 lateral flow test with a negative result before the talk.\n\nLink to join 
 virtually: https://cl-cam-ac-uk.zoom.us/j/97767639783?pwd=T09GcVJxZUNEUFEv
 RnZnbWwxeEwzQT09\n\nThis talk is being recorded.
LOCATION:Lecture Theatre 1\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR