Multi-marginal Gromov–Wasserstein transport and barycentres
Gromov–Wasserstein (GW) distances are combinations of Gromov–Hausdorff and
Wasserstein distances that allow the comparison of two different metric measure spaces …
Wasserstein distances that allow the comparison of two different metric measure spaces …
Geometry of the Space of Partitioned Networks: A Unified Theoretical and Computational Framework
Interactions and relations between objects may be pairwise or higher-order in nature, and so
network-valued data are ubiquitous in the real world. The" space of networks", however, has …
network-valued data are ubiquitous in the real world. The" space of networks", however, has …
Reconstructing the Unseen: GRIOT for Attributed Graph Imputation with Optimal Transport
R Serrano, C Laclau, B Jeudy, C Largeron - Joint European Conference …, 2024 - Springer
In recent years, there has been a significant surge in machine learning techniques,
particularly in the domain of deep learning, tailored for handling attributed graphs …
particularly in the domain of deep learning, tailored for handling attributed graphs …
Optimal transport for graph representation learning
C Vincent-Cuaz - 2023 - theses.hal.science
A key challenge in Machine Learning (ML) is to design models able to learn efficiently from
graphs, characterized by nodes with attributes and a prescribed structure encoding their …
graphs, characterized by nodes with attributes and a prescribed structure encoding their …
[PDF][PDF] Transport Optimal pour l'apprentissage de représentation de graphes
C Vincent-Cuaz - 2023 - theses.hal.science
A key challenge in Machine Learning (ML) is to design models able to learn efficiently from
graphs, characterized by nodes with attributes and a prescribed structure encoding their …
graphs, characterized by nodes with attributes and a prescribed structure encoding their …