BEGIN:VCALENDAR
VERSION:2.0
PRODID:-// - ECPv5.3.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aarms.math.ca
X-WR-CALDESC:Events for
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20230111T153000
DTEND;TZID=UTC:20230111T163000
DTSTAMP:20240423T053642
CREATED:20230106T111103Z
LAST-MODIFIED:20230106T113715Z
UID:7016-1673451000-1673454600@aarms.math.ca
SUMMARY:Atlantic Graph Theory Seminar: Pawel Pralat\, Metropolitan University of Toronto
DESCRIPTION:An Unsupervised Framework for Comparing Graph Embeddings\nThe goal of many machine learning applications is to make predictions or discover new patterns using graph-structured data as feature information. In order to extract useful structural information from graphs\, one might want to try to embed it in a geometric space by assigning coordinates to each node such that nearby nodes are more likely to share an edge than those far from each other. There are many embedding algorithms (based on techniques from linear algebra\, random walks\, or deep learning) and the list constantly grows. As a result\, selecting the best embedding is a challenging task and very often requires domain experts. Our general framework assigns the divergence score to each embedding which\, in an unsupervised learning fashion\, distinguishes good from bad embeddings. In order to benchmark embeddings\, we generalize the Chung-Lu random graph model to incorporate geometry.\n\n\nJoin Zoom Meeting\nhttps://us02web.zoom.us/j/82306017918?pwd=Q0hKTElTMzQxaythWmE3SnhtbGZDUT09\n\nMeeting ID: 823 0601 7918\nPasscode: 045489
URL:https://aarms.math.ca/event/atlantic-graph-theory-seminar-pawel-pralat-metropolitan-university-of-toronto/
LOCATION:Online via Zoom
CATEGORIES:AARMS Atlantic Graph Theory Seminar
ORGANIZER;CN="jeannette%20Janssen":MAILTO:jeannette.janssen@dal.ca
END:VEVENT
END:VCALENDAR