BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20220327T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260405T225053Z
UID:1650895200@ist.ac.at
DTSTART:20220425T160000
DTEND:20220425T170000
DESCRIPTION:Speaker: Olgica Milenkovic\nhosted by Marco Mondelli\nAbstract:
  PageRank (PR) is an algorithm developed by Google for the purpose of gene
 rating website rankings used as part of their search engine systems. Rough
 ly speaking\, PageRank represent a method for aggregating scores of variab
 le-length random walks. Aggregation is performed using weighted combinatio
 ns of walk parameters\, with the weights representing a predetermined func
 tion of a single “diffusion parameter”. Given that many other learning
  and optimization methods rely on random walk aggregation\, various genera
 lizations of PageRank have been proposed in the literature. These generali
 zations rely on optimizing or adapting the weights used in the aggregation
  process to various tasks at hand. Examples include Personalized PageRank 
 and Heat-Kernel PageRank.In the talk\, we discuss two new forms of general
 ized PageRank methods\, Inverse PageRank (IPR) and Adaptive PageRank (APR)
 . IPR offers provable state-of-the-art performance guarantees for local (s
 eed-set) community detection\, while APR can be applied to different graph
  neural network learning tasks as it adaptively learns the aggregation wei
 ghts of random walks. We describe the underlying mathematical principles s
 upporting the parameter selection process and provide numerous experiments
  on synthetic and real datasets that illustrate the performance of the gen
 eralized PageRank methods. This is a joint work with Eli Chien\, Pan Li a
 nd Jianhao Peng.
LOCATION:Online\, ISTA
ORGANIZER:arinya.eller@ist.ac.at
SUMMARY:Olgica Milenkovic: Generalized page rank applications: From local c
 ommunity detection to graph neural networks
URL:https://talks-calendar.ista.ac.at/events/3454
END:VEVENT
END:VCALENDAR