BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Expanding the borders of Multimodal Graph Learning with Sheaf Neur
 al Networks - Mar Gonzàlez i Català
DTSTART:20241126T172000Z
DTEND:20241126T180000Z
UID:TALK224920@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Multimodal graph learning (MGL) has become an emerging topic d
 ue to the prevalence of multimodal graphs (MGs). Numerous types of multimo
 dal data are present in a graph format\, forming MGs where nodes represent
  entities of heterogeneous types and edges indicate connections amongst th
 em. A core challenge in MGL lies in effectively processing and integrating
  knowledge from multiple modalities while navigating the complexities of g
 raph topology. In this talk\, I will review the state-of-the-art approache
 s in MGL and introduce a novel framework: multimodal sheaf neural networks
 . By attaching a cellular sheaf to a standard multimodal graph\, this fram
 ework aims to provide enhanced control over modality fusion\, opening new 
 avenues for more robust and interpretable learning.\n\nThe talk will be st
 reamed: \n\nJoin Zoom Meeting\nhttps://us05web.zoom.us/j/86434473548?pwd=s
 K0aBIJPVgZKbWAREyTfccfa2ppRXk.1\n\nMeeting ID: 864 3447 3548\nPasscode: 6G
 6PSh\n\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR