BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:34386136-3638-4464-b561-313438613566
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Providing Explanations for Unsupervised Graph Learning Models 
 - Hogun Park\, Associate Professor\, Sungkyunkwan University
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20270314T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
RDATE:20261101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20250309T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:8777687d-b171-4b56-ad5e-f1db3354fd66
DTSTAMP:20260416T062724Z
CLASS:PUBLIC
CREATED:20250707T191503Z
DESCRIPTION:Abstract: This talk presents advancements in providing explanat
 ions for unsupervised graph learning models. It highlights eXplainable AI 
 (XAI)'s role in identifying influential subgraphs for graph learning model
 s. A key contribution\, the UNR-Explainer (ICLR 2024) \, generates counter
 factual explanations for unsupervised node representation learning models 
 by using Monte Carlo Tree Search to find important subgraphs. Additionally
 \, the talk introduces the HINT-G framework (upcoming KDD 2025) \, which l
 everages influence functions to explain GNNs across supervised and unsuper
 vised settings…
DTSTART;TZID=America/Vancouver:20250715T164500
DTEND;TZID=America/Vancouver:20250715T174500
LAST-MODIFIED:20250707T191940Z
LOCATION:UBC Vancouver Campus\, Fried Kaiser (KAIS) building\, Room 2020/20
 30\, 2332 Main Mall
SUMMARY:Providing Explanations for Unsupervised Graph Learning Models - Hog
 un Park\, Associate Professor\, Sungkyunkwan University
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/providing-explanations-unsupervised-graph-le
 arning-models-hogun-park-associate-professor
END:VEVENT
END:VCALENDAR