BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Self-Supervised Graph Representation Learning
DTSTART:20230823T100000
DTEND:20230823T120000
DTSTAMP:20260407T111518Z
UID:b77d52db1c1e97100fc9bde817f304338a68d438aaf831e03ada1dd7
CATEGORIES:Conferences - Seminars
DESCRIPTION:Sevda Ögüt\nEDIC candidacy exam\nExam president: Prof. Lenka
  Zdeborová\nThesis advisor: Prof. Pascal Frossard\nThesis co-advisor: Dr.
  Dorina Thanou\nCo-examiner: Prof. Dimitri Van De Ville\n\nAbstract\nComin
 g soon\n\nBackground papers\n1- DeepSMILE: Contrastive self-supervised pr
 e-training benefits MSI and HRD classification directly from H&E whole-sli
 de images in colorectal and breast cancer (https://www.sciencedirect.com/s
 cience/article/abs/pii/S1361841522001116)\n2- Derivation of prognostic co
 ntextual histopathological features from whole-slide images of tumours via
  graph deep learning (https://www.nature.com/articles/s41551-022-00923-0)\
 n3- E(n) Equivariant Graph Neural Networks (http://proceedings.mlr.press/
 v139/satorras21a/satorras21a.pdf)\n 
LOCATION:ELE 242 https://plan.epfl.ch/?room==ELE%20242
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR