BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:62333037-6262-4438-a237-636166613738
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Graph Neural Networks and Graph Isomorphism - Will Hamilton\, 
 Assistant Professor\, McGill University
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20211107T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20190310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20200308T020000
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:571fc023-c588-4727-880b-f8095a74ae0c
DTSTAMP:20260918T001220Z
CLASS:PUBLIC
CREATED:20191203T200106Z
DESCRIPTION:Abstract: In recent years\, graph neural networks (GNNs) have e
 merged as a powerful neural architecture to learn vector representations o
 f nodes and graphs in a supervised\, end-to-end fashion. However\, GNNs ha
 ve mainly been evaluated empirically---showing promising results. This tal
 k will discuss GNNs from a theoretical point of view and relate them to th
 e 1-dimensional Weisfeiler-Leman graph isomorphism heuristic (1-WL). We sh
 ow that GNNs have the same expressiveness as the 1-WL in terms of distingu
 ishing non-isomorphic (sub-)graphs. Hence\, both algorithms also have the 
 same shortcomings…
DTSTART;TZID=America/Vancouver:20191216T140000
DTEND;TZID=America/Vancouver:20191216T150000
LAST-MODIFIED:20210611T170632Z
LOCATION:ICCS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouver\
 , BC
SUMMARY:Graph Neural Networks and Graph Isomorphism - Will Hamilton\, Assis
 tant Professor\, McGill University
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/graph-neural-networks-and-graph-isomorphism-
 will-hamilton-assistant-professor-mcgill
END:VEVENT
END:VCALENDAR