BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Discrete Curvature and Applications in Graph Machine Learning - Me
 lanie Weber\,  Harvard University 
DTSTART:20240112T140000Z
DTEND:20240112T150000Z
UID:TALK210232@talks.cam.ac.uk
CONTACT:AI Aviles-Rivero
DESCRIPTION:The problem of identifying geometric structure in heterogeneou
 s\, high-dimensional data is a cornerstone of Representation Learning. In 
 this talk\, we study this problem from the perspective of Discrete Geometr
 y. We start by reviewing discrete notions of curvature with a focus on Ric
 ci curvature. Then we discuss how curvature characterizations of graphs ca
 n be used to improve the efficiency of Graph Neural Networks. Specifically
 \, we propose curvature-based rewiring and encoding approaches and study t
 heir impact on the Graph Neural Network’s downstream performance through
  theoretical and computational analysis. We further discuss applications o
 f discrete Ricci curvature in Manifold Learning\, where discrete-to-contin
 uum consistency results allow for characterizing the geometry of a suitabl
 e embedding space both locally and in the sense of global curvature bounds
 . Based on joint work with Lukas Fesser and Nicolás García Trillos.
LOCATION:zoom-- Contact organiser for the link
END:VEVENT
END:VCALENDAR