BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:593@lincs.fr
DTSTART;TZID=Europe/Paris:20201217T140000
DTEND;TZID=Europe/Paris:20201217T170000
DTSTAMP:20201214T073511Z
URL:https://www.lincs.fr/events/thesis-defense-deep-learning-techniques-fo
 r-graph-embedding-at-different-scales/
SUMMARY:Thesis defense "Deep learning techniques for graph embedding at
 different scales"
DESCRIPTION:In many scientific fields\, studied data have an underlying
 graph or manifold structure such as communication networks (whether social
 or technical)\, knowledge graphs or molecules. A graph is composed of
 nodes\, also called vertices\, con- nected together by edges. Recently\,
 deep learning algorithms have become state-of-the-art models in many fields
 and in particular in natural language processing and image analysis. It led
 the way to a great line of studies to generalize deep learning models to
 graphs. In particular\, several formulations of convolutional neural
 networks were proposed and research is carried to develop new layers and
 network architectures to graphs. Those models aim at solving different
 tasks such as node classification\, link prediction or graph
 classification. In this work\, we study node\, subgraph or graph embeddings
 produced by graph neural networks. These embeddings at different scales
 encode hierarchical represen- tations of graphs. Based on these embedding
 techniques\, we propose new deep learning architectures to tackle node
 classification or graph classification tasks. We study several applications
 of these new techniques. For example\, we study the problem of having a
 graph embedding invariant by node permutation and the interpretability of
 graph neural networks.\n\nHere's the details to follow it on
 GoToMeeting:\n\nParticipez à ma réunion depuis votre ordinateur\,
 tablette ou
 smartphone.&nbsp\;https://global.gotomeeting.com/join/962144589&nbsp\;Vous
 pouvez aussi appeler à l'aide de votre
 téléphone.&nbsp\;États-Unis:&nbsp\;+1 (872) 240-3311&nbsp\;Code
 d'accès:&nbsp\;962-144-589&nbsp\;Rejoignez la réunion depuis une salle ou
 un système de vidéoconférence.&nbsp\;Composez ou tapez : 67.217.95.2
 ou&nbsp\;inroomlink.goto.com&nbsp\;ID réunion: 962 144 589&nbsp\;Ou
 appelez directement:&nbsp\;962144589@67.217.95.2&nbsp\;ou
 67.217.95.2##962144589&nbsp\;Vous n'utilisez pas encore GoToMeeting&nbsp\;?
 Téléchargez l’application dès maintenant et soyez prêt pour votre
 première
 réunion&nbsp\;:&nbsp\;https://global.gotomeeting.com/install/962144589\n&n
 bsp\;\n&nbsp\;
CATEGORIES:PhD Defense
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20201025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR