136 citations · 207 across the 24 of their papers we have counts for
11 papers · 1 filter
Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity
Pierre Houedry, Nicolas Courty, Florestan Martin-Baillon +2
Trees and the associated shortest-path tree metrics provide a powerful framework for representing hierarchical and combinatorial structures in data. Given an arbitrary metric space…
PASCO (PArallel Structured COarsening): an overlay to speed up graph clustering algorithms
Etienne Lasalle, Rémi Vaudaine, Titouan Vayer +4
Clustering the nodes of a graph is a cornerstone of graph analysis and has been extensively studied. However, some popular methods are not suitable for very large graphs: e.g., spe…
Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure
Can Pouliquen, Mathurin Massias, Titouan Vayer
Estimating matrices in the symmetric positive-definite (SPD) cone is of interest for many applications ranging from computer vision to graph learning. While there exist various con…
Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein
Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty +3
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR)…
Interpolating between Clustering and Dimensionality Reduction with Gromov-Wasserstein
Hugues Van Assel, Cédric Vincent-Cuaz, Titouan Vayer +2
We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances betwee…
Optimal Transport with Adaptive Regularisation
Hugues Van Assel, Titouan Vayer, Remi Flamary +1
Regularising the primal formulation of optimal transport (OT) with a strictly convex term leads to enhanced numerical complexity and a denser transport plan. Many formulations impo…
Implicit Differentiation for Hyperparameter Tuning the Weighted Graphical Lasso
Can Pouliquen, Paulo Gonçalves, Mathurin Massias +1
We provide a framework and algorithm for tuning the hyperparameters of the Graphical Lasso via a bilevel optimization problem solved with a first-order method. In particular, we de…
SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
Hugues Van Assel, Titouan Vayer, Rémi Flamary +1
Many approaches in machine learning rely on a weighted graph to encode the similarities between samples in a dataset. Entropic affinities (EAs), which are notably used in the popul…
Template based Graph Neural Network with Optimal Transport Distances
Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli +2
Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized fo…
Semi-relaxed Gromov-Wasserstein divergence with applications on graphs
Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli +2
Comparing structured objects such as graphs is a fundamental operation involved in many learning tasks. To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transpor…
Online Graph Dictionary Learning
Cédric Vincent-Cuaz, Titouan Vayer, Rémi Flamary +2
Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements. Yet, this analysis is not amenable in the context…