BEGIN:VCALENDAR
VERSION:2.0
X-WR-TIMEZONE:Europe/Paris
CALSCALE:GREGORIAN
PRODID:-//SPIP/Plugin Agenda//NONSGML v1.0//FR
X-WR-CALNAME;VALUE=TEXT: -- Institut de Mathématiques de Marseille\, UMR 7373
X-WR-RELCALID:https://www.i2m.univ-amu.fr/spip.php?page=article&id_article=0
BEGIN:VEVENT
SUMMARY:Titouan VAYER - Optimal transport for structured data
UID:20190207T154434-a128-e2753@https://www.i2m.univ-amu.fr
DTSTAMP:20190207T154434
DTSTART:20190308T140000
DTEND:20190308T150000
CREATED:20190207T154434
ATTENDEE;CN=Titouan VAYER:mailto:no-reply@math.cnrs.fr
LAST-MODIFIED:20190218T085618
LOCATION:CMI\, salle de séminaire R164 (1er étage)
DESCRIPTION:In this work\, we consider the problem of computing distances between structured objects such as undirected graphs\, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. which minimizes a total cost of transporting probability masses) that unveils the geometric nature of the structured objects space. After introducing Wasserstein and Gromov-Wasserstein metrics that focus solely and respectively on features (by considering a metric in the feature space) or structure (by seeing structure as a metric space)\, we will present our new distance which exploits jointly both information\, and consequently being called Fused Gromov-Wasserstein (FGW). We will discuss its properties and computational aspects\, we show results on a graph classification task\, where our method outperforms both graph kernels and deep graph convolutional networks. Exploiting further on the metric properties of FGW\, interesting geometric objects such as Fréchet means or barycenters of graphs are illustrated and discussed in a clustering context. https://tvayer.github.io Titouan VAYER [
CATEGORIES:(Séminaire Signal et Apprentissage|textebrut|filtrer_ical)]
URL:https://www.i2m.univ-amu.fr/Seminaire-Signal-et-Apprentissage?id_evenement=2753
SEQUENCE:1
STATUS:CONFIRMED
END:VEVENT