BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Cambridge Image Analysis Seminars
SUMMARY:Discrete Curvature and Applications in Graph Machi
ne Learning - Melanie Weber\, Harvard University
DTSTART;TZID=Europe/London:20240112T140000
DTEND;TZID=Europe/London:20240112T150000
UID:TALK210232AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/210232
DESCRIPTION:The problem of identifying geometric structure in
heterogeneous\, high-dimensional data is a corners
tone of Representation Learning. In this talk\, we
study this problem from the perspective of Discre
te Geometry. We start by reviewing discrete notion
s of curvature with a focus on Ricci curvature. Th
en we discuss how curvature characterizations of g
raphs can be used to improve the efficiency of Gra
ph Neural Networks. Specifically\, we propose curv
ature-based rewiring and encoding approaches and s
tudy their impact on the Graph Neural Network’s do
wnstream performance through theoretical and compu
tational analysis. We further discuss applications
of discrete Ricci curvature in Manifold Learning\
, where discrete-to-continuum 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
CONTACT:AI Aviles-Rivero
END:VEVENT
END:VCALENDAR