BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240331T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.27600.field_data.0@www.open.diag.uniroma1.it
DTSTAMP:20260407T051820Z
CREATED:20240108T114628Z
DESCRIPTION:AbstractGraph Neural Networks (GNNs) have become the leading pa
 radigm for learning on (static) graph-structured data. However\, many real
 -world systems are dynamic in nature\, since the graph and node/edge attri
 butes change over time. In recent years\, GNN-based models for temporal gr
 aphs have emerged as a promising area of research to extend the capabiliti
 es of GNNs. In this work\, we provide the first comprehensive overview of 
 the current state-of-the-art of temporal GNN\, introducing a rigorous form
 alization of learning settings and tasks and a novel taxonomy categorizing
  existing approaches in terms of how the temporal aspect is represented an
 d processed. We conclude the survey with a discussion of the most relevant
  open challenges for the field\, from both research and application perspe
 ctives. Speaker's short bio: Antonio Longa is an Assistant Professor (RTD-
 A) at the University of Trento\, actively engaged in research within the S
 tructured Machine Learning (SML) Group led by Andrea Passerini. He earned 
 his Ph.D. with honors from the University of Trento and Fondazione Bruno K
 essler\, under the mentorship of Bruno Lepri.  Link per zoom meeting:https
 ://uniroma1.zoom.us/j/81785452099ID riunione: 817 8545 2099
DTSTART;TZID=Europe/Paris:20240115T160000
DTEND;TZID=Europe/Paris:20240115T160000
LAST-MODIFIED:20240108T132225Z
LOCATION:DIAG\, Room B101
SUMMARY:Seminar on Graph Neural Networks for temporal graphs: State of the 
 art\, open challenges\, and opportunities - Antonio Longa
URL;TYPE=URI:http://www.open.diag.uniroma1.it/node/27600
END:VEVENT
END:VCALENDAR