no code implementations • 2 Mar 2023 • Jason Piquenot, Aldo Moscatelli, Maxime Bérar, Pierre Héroux, Romain Raveaux, Jean-Yves Ramel, Sébastien Adam
This paper introduces a framework for formally establishing a connection between a portion of an algebraic language and a Graph Neural Network (GNN).
no code implementations • 19 Feb 2020 • Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso, Alain Rakotomamonjy
Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we consider a method allowing to embed the metric measure spaces in a common Euclidean space and compute an optimal transport (OT) on the embedded distributions.
1 code implementation • NeurIPS 2019 • Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso, Alain Rakotomamonjy
We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures.