BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Optimal Transport for graph representation : from unsupervised lea
 rning to graph prediction - Remi Flamary (École Polytechnique)
DTSTART:20250508T081500Z
DTEND:20250508T091500Z
UID:TALK230476@talks.cam.ac.uk
DESCRIPTION:In recent years\, the Optimal Transport (OT) based Gromov-Wass
 erstein (GW) divergence has been investigated as a similarity measure betw
 een structured data such as graphs seen as distributions typically lying i
 n different metric spaces. In this talk\, we discuss the optimization prob
 lem inherent in the computation of GW and some of its recent extensions\, 
 such as Entropic\, Fused and semi-relaxed GW divergences. Next we will ill
 ustrate how these OT problems can be used in machine learning applications
  to learn graph representations for graph compression\, clustering\, class
 ification and structured prediction.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR