English
Related papers

Related papers: Gromov-Wasserstein at Scale, Beyond Squared Norms

200 papers

Multi-view data analysis seeks to integrate multiple representations of the same samples in order to recover a coherent low-dimensional structure. Classical approaches often rely on feature concatenation or explicit alignment assumptions,…

Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph…

Machine Learning · Computer Science 2023-10-05 Xinyu Ma , Xu Chu , Yasha Wang , Yang Lin , Junfeng Zhao , Liantao Ma , Wenwu Zhu

Gromov--Wasserstein optimal transport (GWOT) aligns metric measure spaces by matching their within-domain relational structures, but large-scale GWOT remains challenging because its objective is nonconvex and projection onto the transport…

Machine Learning · Computer Science 2026-05-07 Ling Liang , Lei Yang

Dimension reduction techniques typically seek an embedding of a high-dimensional point cloud into a low-dimensional Euclidean space which optimally preserves the geometry of the input data. Based on expert knowledge, one may instead wish to…

Optimization and Control · Mathematics 2025-02-28 Ranthony A. Clark , Tom Needham , Thomas Weighill

We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a novel and theoretically-supported paradigm for large-scale graph analysis. The proposed method is based on the fact that Gromov-Wasserstein discrepancy is a…

Machine Learning · Computer Science 2019-10-10 Hongteng Xu , Dixin Luo , Lawrence Carin

Graph coarsening is a technique for solving large-scale graph problems by working on a smaller version of the original graph, and possibly interpolating the results back to the original graph. It has a long history in scientific computing…

Machine Learning · Computer Science 2023-06-16 Yifan Chen , Rentian Yao , Yun Yang , Jie Chen

The Gromov-Wasserstein (GW) variant of optimal transport, designed to compare probability densities defined over distinct metric spaces, has emerged as an important tool for the analysis of data with complex structure, such as ensembles of…

Machine Learning · Statistics 2025-08-15 Mary Chriselda Antony Oliver , Emmanuel Hartman , Tom Needham

Dimension reduction algorithms are a crucial part of many data science pipelines, including data exploration, feature creation and selection, and denoising. Despite their wide utilization, many non-linear dimension reduction algorithms are…

Machine Learning · Statistics 2024-08-06 Ryan Murray , Adam Pickarski

Analyzing relationships between objects is a pivotal problem within data science. In this context, Dimensionality reduction (DR) techniques are employed to generate smaller and more manageable data representations. This paper proposes a new…

Machine Learning · Statistics 2025-07-08 Rafael P. Eufrazio , Eduardo Fernandes Montesuma , Charles C. Cavalcante

Recently, two concepts from optimal transport theory have successfully been brought to the Gromov--Wasserstein (GW) setting. This introduces a linear version of the GW distance and multi-marginal GW transport. The former can reduce the…

Numerical Analysis · Mathematics 2022-11-16 Florian Beier , Robert Beinert

Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve…

Machine Learning · Computer Science 2025-08-20 Théo Uscidda , Luca Eyring , Karsten Roth , Fabian Theis , Zeynep Akata , Marco Cuturi

The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces. Calculating essentially the mutual departure from isometry, it has found vast usage in domain translation…

Machine Learning · Statistics 2024-12-23 Anish Chakrabarty , Arkaprabha Basu , Swagatam Das

In this paper, we newly formulate and solve the optimal density control problem with Gromov-Wasserstein (GW) terminal cost in discrete-time linear Gaussian systems. Differently from the Wasserstein or Kullback-Leibler distances employed in…

Optimization and Control · Mathematics 2024-05-06 Kohei Morimoto , Kenji Kashima

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…

Machine Learning · Computer Science 2025-06-30 Hugues Van Assel , Cédric Vincent-Cuaz , Nicolas Courty , Rémi Flamary , Pascal Frossard , Titouan Vayer

The Gromov-Wasserstein (GW) distance is a powerful tool for comparing metric measure spaces which has found broad applications in data science and machine learning. Driven by the need to analyze datasets whose objects have increasingly…

Metric Geometry · Mathematics 2026-03-10 Martin Bauer , Facundo Mémoli , Tom Needham , Mao Nishino

We introduce a theoretical framework for performing statistical tasks---including, but not limited to, averaging and principal component analysis---on the space of (possibly asymmetric) matrices with arbitrary entries and sizes. This is…

Metric Geometry · Mathematics 2020-04-24 Samir Chowdhury , Tom Needham

Gromov-Wasserstein (GW) is a powerful tool to compare probability measures whose supports are in different metric spaces. GW suffers however from a computational drawback since it requires to solve a complex non-convex quadratic program. We…

Machine Learning · Statistics 2020-06-18 Tam Le , Nhat Ho , Makoto Yamada

We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a…

Machine Learning · Computer Science 2023-10-06 Hugues Van Assel , Cédric Vincent-Cuaz , Titouan Vayer , Rémi Flamary , Nicolas Courty

Gromov-Wasserstein distance has found many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariance…

Machine Learning · Computer Science 2023-07-20 Pinar Demetci , Quang Huy Tran , Ievgen Redko , Ritambhara Singh

This paper considers the problem of estimating a matrix that encodes pairwise distances in a finite metric space (or, more generally, the edge weight matrix of a network) under the barycentric coding model (BCM) with respect to the…

Optimization and Control · Mathematics 2026-03-31 Rocío Díaz Martín , Ivan V. Medri , James M. Murphy