BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261004T150253EDT-0983oUb6uh@132.216.98.100
DTSTAMP:20261004T190253Z
DESCRIPTION:Virtual Informal Systems Seminar (VISS) Centre for Intelligent 
 Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decision
 s (GERAD)\n\nSpeaker: William Hamilton\, Assistant Professor\, School of C
 omputer Science\, McGill University\n\n\n	Zoom Link\n	Meeting ID: 910 7928 6
 959        Passcode: VISS\n\n\n	Abstract: \n\nGraph-structured data is ubiq
 uitous throughout the natural and social sciences\, from telecommunication
  networks to quantum chemistry. Building relational inductive biases into 
 deep learning architectures is crucial if we want systems that can learn\,
  reason\, and generalize from this kind of data. Recent years have seen a 
 surge in research on graph representation learning\, most prominently in t
 he development of graph neural networks (GNNs). Advances in GNNs have led 
 to state-of-the-art results in numerous domains\, including chemical synth
 esis\, 3D-vision\, recommender systems\, question answering\, and social n
 etwork analysis. In the first part of this talk I will provide an overview
  and summary of recent progress in this fast-growing area\, highlighting f
 oundational methods and theoretical motivations. In the second part of thi
 s talk I will discuss fundamental limitations of the current GNN paradigm.
  Finally\, I will conclude the talk by discussing recent progress my group
  has made in advancing graph representation learning beyond the GNN paradi
 gm.\n	\n	Bio:\n\nWilliam (Will) Hamilton is an Assistant Professor in the Sc
 hool of Computer Science at McGill University\, a Canada CIFAR AI Chair\, 
 and a member of the Mila AI Institute of Quebec. Will completed his PhD in
  Computer Science at Stanford University in 2018. He received the 2018 Art
 hur Samuel Thesis Award for best Computer Science PhD Thesis from Stanford
  University\, the 2014 CAIAC MSc Thesis Award for best AI-themed MSc thesi
 s in Canada\, as well as an honorable mention for the 2013 ACM Undergradua
 te Researcher of the Year. His interests lie at the intersection of machin
 e learning\, network science\, and natural language processing\, with a cu
 rrent emphasis on the fast-growing subject of graph representation learnin
 g.\n
DTSTART:20201204T160000Z
DTEND:20201204T170000Z
LOCATION:CA\, ZOOM
SUMMARY:Graph Representation Learning: Recent Advances and Open Challenges
URL:https://www.mcgill.ca/cim/channels/event/graph-representation-learning-
 recent-advances-and-open-challenges-326555
END:VEVENT
END:VCALENDAR