Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tackle various challenging problems arising in the field. Firstly, we study how to leverage the inherent local community structure of graphs while learning node representations. We learn enhanced community-aware representations by combining the latent information with the embeddings. Moreover, we concentrate on the expressive- ness of node representations. We emphasize exponential family distributions to capture rich interaction patterns. We propose a model that combines random walks with kernelized matrix factorization. In the last part of the thesis, we study models balancing the trade-off between efficiency and accuracy. We propose a scalable...
In the last few years, graphs have become an instinctive representative tool to better study complex...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
L'objectif principal de l'Apprentissage de Représentations sur Graphes est de plonger les nœuds dans...
L'objectif principal de l'Apprentissage de Représentations sur Graphes est de plonger les nœuds dans...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
In the last few years, graphs have become an instinctive representative tool to better study complex...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
Graph Representation Learning aims to embed nodes in a low-dimensional space. In this thesis, we tac...
L'objectif principal de l'Apprentissage de Représentations sur Graphes est de plonger les nœuds dans...
L'objectif principal de l'Apprentissage de Représentations sur Graphes est de plonger les nœuds dans...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceGraph Representation Learning (GRL) has become a key paradigm in network analy...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
In the last few years, graphs have become an instinctive representative tool to better study complex...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...
International audienceRepresenting networks in a low dimensional latent space is a crucial task with...