Tutoriel DeepLorIA – Dynamic Graph Neural Networks: Learning from Evolving Graphs

DeepLorIA est un réseau interne destiné au partage des connaissances en matière d’intelligence artificielle, quel que soit le domaine d’application.

Le prochain tutoriel DeepLorIA aura lieu le mercredi 17 septembre de 14 h à 16 h en salle A008 du Loria, avec Mohammed Khatbane, doctorant dans l’équipe Capsid du Loria, avec une présentation intitulée Dynamic Graph Neural Networks: Learning from Evolving Graphs.

This tutorial aims to introduce dynamic graph neural networks (DGNNs) and their applications in modeling evolving graphs over time.
In the presentation session, you’ll learn the basics of Graph Neural Networks (GNNs), understand the difference between static and dynamic graphs, explore dynamic graph representation learning, and become familiar with key DGNN architectures. In the practical session, you’ll apply these concepts hands-on: preparing temporal graph data, implementing a DGNN model, training and evaluating it, and visualizing temporal node embeddings. By the end, you will be able to experiment with dynamic graphs and build models that capture temporal dynamics in data.

Lien d’inscription. Toute personne extérieure au Loria doit s’inscrire avant le 13 octobre.