BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:AI Center Seminar Series - Prof. Michael Bronstein
DTSTART:20240201T153000
DTEND:20240201T170000
DTSTAMP:20260510T185712Z
UID:3b5a675e7b4da2accada236ba7554caadf0630f73171943dee2adb10
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Michael Bronstein\n\nTitle\nA Physical perspective on Gr
 aph Neural Networks \n\nAbstract\nThe message-passing paradigm has been t
 he “battle horse” of deep learning on graphs for several years\, makin
 g graph neural networks a big success in a wide range of applications\, fr
 om particle physics to protein design. From a theoretical viewpoint\, ite
 stablished the link to the Weisfeiler-Lehman hierarchy\, allowing to 
 analyse the expressive power of GNNs. We argue that the very “node-and-
 edge”-centric mindset of current graph deep learning schemes may hinder 
 future progress in the field. As an alternative\, we propose physics-inspi
 red “continuous” learning models that open up a new trove of tools f
 rom the fields of differential geometry\, algebraic topology\, and differe
 ntial equations so far largely unexplored in graph ML.\n\nBio: https:/
 /www.cs.ox.ac.uk/people/michael.bronstein/\nMichael Bronstein is the DeepM
 ind Professor of AI at the University of Oxford. He was previously Head of
  Graph Learning Research at Twitter\, a professor at Imperial College Lond
 on and held visiting appointments at Stanford\, MIT\, and Harvard. He has 
 been affiliated with three Institutes for Advanced Study (at TUM as a Rudo
 lf Diesel Fellow (2017-2019)\, at Harvard as a Radcliffe fellow (2017-2018
 )\, and at Princeton as a short-time scholar (2020)). Michael received his
  PhD from the Technion in 2007. He is the recipient of the EPSRC Turing AI
  World Leading Research Fellowship\, Royal Society Wolfson Research Merit 
 Award\, Royal Academy of Engineering Silver Medal\, five ERC grants\, two 
 Google Faculty Research Awards\, and two Amazon AWS ML Research Awards. He
  is a Member of the Academia Europaea\, Fellow of IEEE\, IAPR\, BCS\, and 
 ELLIS\, ACM Distinguished Speaker\, and World Economic Forum Young Scienti
 st. In addition to his academic career\, Michael is a serial entrepreneur 
 and founder of multiple startup companies\, including Novafora\, Invision 
 (acquired by Intel in 2012)\, Videocites\, and Fabula AI (acquired by Twit
 ter in 2019).\n\nReplay available on YouTube.
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202 https://www.youtube
 .com/watch?v=kEyLUY8A5zo
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR