News

Title: Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity Abstract: ‘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, its deviation from a tree metric can be quantified by Gromov’s \delta-hyperbolicity.

title: Multi-Prototype Hyperbolic Learning Guided by Class Hierarchy Abstract: In many computer vision applications, datasets often exhibit an underlying taxonomy within the label space. To adhere to this hierarchical structure, hyperbolic spaces have emerged as an effective manifold for representation learning, thanks to their ability to encode hierarchical relationships, with little distortion, even for low-dimensional embeddings.

Title: Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein Abstract: Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing points into meaningful clusters (clustering).

A link to the paper can be found here : paper

The paper from Paul ‘Horospherical Learning with Smart prototypes’ has just been accepted as an oral at BMVC 2024.

Our paper first authored by Baptiste Genest ‘Non-Euclidean Sliced Optimal Transport Sampling’ has just received the Günter Enderle best paper award at Eurographics 2024. See a related article (in French) .