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.27639.field_data.0@www.open.diag.uniroma1.it
DTSTAMP:20260411T125742Z
CREATED:20240205T172650Z
DESCRIPTION:Abstract:The talk provides an overview of a master's thesis and
  ongoing project titled 'Nonlinear Sheaf Diffusion in Graph Neural Network
 s'. The study focuses on exploring the potential benefits of introducing n
 onlinearity in the Laplacian of Sheaf Neural Networks when dealing with no
 de classification tasks on graphs.  After understanding the motivation\, w
 hich arises from the area of Opinion Dynamics\, we will transition to a th
 eoretical analysis of such nonlinearity and then discuss the practical uti
 lity of the proposed technique. The project has been driven by thorough ex
 perimental validation\, in order to confirm the practical effectiveness of
  the methodology and guide the design of different versions of the model. 
 The starting point for this project is 'Neural Sheaf Diffusion'\, a previo
 us work by Cristian Bodnar et al.\, in which a Sheaf Neural Network model 
 is designed to address common issues in Graph Neural Networks\, such as ov
 ersmoothing and heterophily. Their contributions have served as inspiratio
 n for this thesis\, opening new research directions in Topological Deep Le
 arning\, a field that enhances our understanding of complex data structure
 s from a topological perspective. Bio:Olga Zaghen received her MSc in Arti
 ficial Intelligence Systems at University of Trento\, where she developed 
 her interest for Geometric Deep Learning. Before that\, she earned her BSc
  in Mathematics at University of Milan. She wrote her MSc thesis on Sheaf 
 Neural Networks at University of Cambridge under the supervision of Prof. 
 Pietro Liò and Prof. Andrea Passerini. She recently completed a research i
 nternship at KAIST in the Vision and Learning Laboratory\, supervised by P
 rof. Seunghoon Hong\, where she focused on random walks for graph represen
 tation learning.
DTSTART;TZID=Europe/Paris:20240219T160000
DTEND;TZID=Europe/Paris:20240219T160000
LAST-MODIFIED:20240205T191325Z
LOCATION:DIAG\, Room B203
SUMMARY:Talk: Nonlinear Sheaf Diffusion in Graph Neural Networks - Olga Zag
 hen
URL;TYPE=URI:http://www.open.diag.uniroma1.it/node/27639
END:VEVENT
END:VCALENDAR