BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Sheaves for Heterogeneous Data - Luke Braithwaite
DTSTART:20240927T160000Z
DTEND:20240927T170000Z
UID:TALK221617@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Heterogeneous graphs\, with nodes and edges of different types
 \, are commonly used to model relational structures in many real-world app
 lications\, such as social networks\, recommendation systems\, and bioinfo
 rmatics. Current heterogeneous graph neural networks have focused on accou
 nting for the heterogeneity in the model architecture\, leading to increas
 ingly complex models. This talk discusses a novel approach that uses cellu
 lar sheaves to model the heterogeneity in the graph's underlying topology 
 and achieves competitive benchmark results while being more parameter-effi
 cient.
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR