BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260622T124735Z
UID:6a358154ee7fd120793416@ist.ac.at
DTSTART:20260625T113000
DTEND:20260625T123000
DESCRIPTION:Speaker: Aurora Rossi\nAbstract: This talk introduces Temporal 
 Graph Neural Networks (TGNNs) as models for learning from systems that com
 bine relational structure and temporal dynamics. Starting from basic neura
 l network concepts\, we build up to graph neural networks\, message passin
 g\, and temporal graph settings\, distinguishing between static graphs wit
 h time-varying features and fully evolving graph structures. Through examp
 les in synthetic forecasting\, traffic prediction\, and brain activity mod
 eling\, the tutorial illustrates when graph information can improve tempor
 al learning and how TGNNs capture spatio-temporal dependencies in real-wor
 ld networks.
LOCATION:Office Bldg West / Ground floor / Heinzel Seminar Room (I21.EG.101
 )\, ISTA
ORGANIZER:joanders@ist.ac.at
SUMMARY:Aurora Rossi: TCS Seminar - An Introduction to Temporal Graph Neura
 l Networks
URL:https://talks-calendar.ista.ac.at/events/6528
END:VEVENT
END:VCALENDAR