Partagez sur
STAGE Representation and contrastive learning on graphs
Date de mise à jour de l’offre
ECOLE NORMALE SUPERIEURE PARIS-SACLAY :
Centre Borelli et une structure de recherche de l'ENS Paris-Saclay. Plus d'info : https://ens-paris-saclay.fr/recherche/laboratoires-et-instituts/centre-borelli
Description de la mission
In the literature, numerous graph neural network (GNN) models have been proposed for graph-related tasks, such as node classification, link prediction, and graph classification. Most existing GNN approaches use semi-supervised training. For many real-world graph applications, e.g. protein analysis, they intuitively require the input of some amount of labeled data.
Alternatively, there is a series of random walk-based GNNs, including node2vec and graph2vec,
which are unsupervised. Their approach is to first learn the node embeddings, and then various supervised downstream tasks are directly applied on these node embeddings. These approaches can be considered as part of the contrastive learning framework.
Contrastive learning originally aims to learn to embed each image in a self-supervised manner. Due to its impressive performance in many tasks, contrastive learning has become the hottest topic in unsupervised learning. Its motivation is to maximize the similarity of positive pairs and the distance of negative pairs. Generally speaking, the positive pairs are composed of data augmentations of the same instance, while those of different instances are regarded as negative pairs.
This internship aims to investigate the last findings in graph embedding and graph contrastive learning, understand, deconstruct the different steps, and make some steps towards new contrastive learning approaches for graphs.
Alternatively, there is a series of random walk-based GNNs, including node2vec and graph2vec,
which are unsupervised. Their approach is to first learn the node embeddings, and then various supervised downstream tasks are directly applied on these node embeddings. These approaches can be considered as part of the contrastive learning framework.
Contrastive learning originally aims to learn to embed each image in a self-supervised manner. Due to its impressive performance in many tasks, contrastive learning has become the hottest topic in unsupervised learning. Its motivation is to maximize the similarity of positive pairs and the distance of negative pairs. Generally speaking, the positive pairs are composed of data augmentations of the same instance, while those of different instances are regarded as negative pairs.
This internship aims to investigate the last findings in graph embedding and graph contrastive learning, understand, deconstruct the different steps, and make some steps towards new contrastive learning approaches for graphs.
Profil recherché
Applied Maths or Informatics. This is an internship for a student to finalize his/her M2 program. Possibility to continue in a PhD thesis .
Niveau de qualification requis
Bac + 4/5 et +
Les offres de stage ou de contrat sont définies par les recruteurs eux-mêmes.
En sa qualité d’hébergeur dans le cadre du dispositif des « 100 000 stages », la Région Île-de-France est soumise à un régime de responsabilité atténuée prévu aux articles 6.I.2 et suivants de la loi n°2204-575 du 21 juin 2004 sur la confiance dans l’économie numérique.
La Région Île-de-France ne saurait être tenue responsable du contenu des offres.
Néanmoins, si vous détectez une offre frauduleuse, abusive ou discriminatoire vous pouvez la signaler
en cliquant sur ce lien.
-
EmployeurECOLE NORMALE SUPERIEURE PARIS-SACLAY
-
Secteur d’activité de la structureEnseignement - Formation - Recherche
-
Effectif de la structureDe 51 à 250 salariés
-
Site internet de la structurehttp://www.centreborelli.fr
-
Type de stage ou contratContrat d'apprentissage
-
Date prévisionnelle de démarrage
-
Durée du stage ou contratPlus de 4 mois et jusqu'à 6 mois
-
Le stage est-il rémunéré ?Oui
-
Niveau de qualification requis
Bac + 4/5 et + -
Lieu du stage4 Avenue des Sciences 91190 2e étage Bâtiment Nord
91190 GIF SUR YVETTE -
Accès et transportsRERB et bus