Apprentissage de représentation pour la diffusion d'Information dans les réseaux sociaux

Modeling the diffusion of information on social media has mainly been treated as a diffusion process on known graphs, and under closed world assumptions. We introduce here a new approach to this problem whose principle is to learn a mapping of the observed interacting users onto a latent representation space in such a way that information diffusion can be modeled efficiently using a heat diffusion process. Since its parameters are directly learned from cascade samples , the model does not rely on any pre-existing diffusion structure. Experiments show the effectiveness of the proposed ideas both in terms of prediction quality and inference speed. MOTS-CLÉS : Apprentissage automatique, Diffusion de l’Information, Réseaux sociaux