English
Related papers

Related papers: A Regularized Wasserstein Framework for Graph Kern…

200 papers

We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. The approach is based on Wasserstein information geometry. It defines a parametrization invariant…

Machine Learning · Computer Science 2021-02-16 Alex Tong Lin , Wuchen Li , Stanley Osher , Guido Montufar

In many real-world contexts, such as social or transport networks, data exhibit both structural connectivity and node-level attributes. For example, roads in a transport network can be characterized not only by their connectivity but also…

Methodology · Statistics 2025-12-18 Ioana Gavra , Ketsia Guichard-Sustowski , Loïc Le Marrec

Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized form of pooling. The structural (or topological) information…

Machine Learning · Computer Science 2022-06-01 Cédric Vincent-Cuaz , Rémi Flamary , Marco Corneli , Titouan Vayer , Nicolas Courty

The Gromov-Wasserstein (GW) framework adapts ideas from optimal transport to allow for the comparison of probability distributions defined on different metric spaces. Scalable computation of GW distances and associated matchings on graphs…

Machine Learning · Computer Science 2021-05-05 Samir Chowdhury , David Miller , Tom Needham

Graph kernels used to be the dominant approach to feature engineering for structured data, which are superseded by modern GNNs as the former lacks learnability. Recently, a suite of Kernel Convolution Networks (KCNs) successfully…

Machine Learning · Computer Science 2024-02-12 Meng-Chieh Lee , Lingxiao Zhao , Leman Akoglu

Finding the mean of sampled data is a fundamental task in machine learning and statistics. However, in cases where the data samples are graph objects, defining a mean is an inherently difficult task. We propose a novel framework for…

Machine Learning · Statistics 2024-03-04 Isabel Haasler , Pascal Frossard

When learning graph neural networks (GNNs) in node-level prediction tasks, most existing loss functions are applied for each node independently, even if node embeddings and their labels are non-i.i.d. because of their graph structures. To…

Machine Learning · Computer Science 2024-03-14 Minjie Cheng , Hongteng Xu

This paper presents a groundbreaking approach to causal inference by integrating continuous normalizing flows (CNFs) with parametric submodels, enhancing their geometric sensitivity and improving upon traditional Targeted Maximum Likelihood…

Machine Learning · Computer Science 2024-02-02 Kaiwen Hou

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 Transport (OT), has proven to be successful in handling the specific…

Machine Learning · Computer Science 2022-03-02 Cédric Vincent-Cuaz , Rémi Flamary , Marco Corneli , Titouan Vayer , Nicolas Courty

This paper presents a robust and efficient method for tracking topological features in time-varying scalar data. Structures are tracked based on the optimal matching between persistence diagrams with respect to the Wasserstein metric. This…

Image and Video Processing · Electrical Eng. & Systems 2019-01-03 Maxime Soler , Mélanie Plainchault , Bruno Conche , Julien Tierny

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

Generative Adversarial Networks are a popular method for learning distributions from data by modeling the target distribution as a function of a known distribution. The function, often referred to as the generator, is optimized to minimize…

Machine Learning · Computer Science 2021-11-03 Daria Reshetova , Yikun Bai , Xiugang Wu , Ayfer Ozgur

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

Machine Learning · Computer Science 2026-05-15 Ao Xu , Tieru Wu

Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various…

Machine Learning · Computer Science 2018-11-15 Marco Cuturi , Gabriel Peyré

Wasserstein gradient and Hamiltonian flows have emerged as essential tools for modeling complex dynamics in the natural sciences, with applications ranging from partial differential equations (PDEs) and optimal transport to quantum…

Numerical Analysis · Mathematics 2025-11-11 Jianyu Hu , Juan-Pablo Ortega , Daiying Yin

Metro networks serve as good examples of traffic systems for understanding the relations between geometric structures and transport properties.We study and compare 28 world major metro networks in terms of the Wasserstein distance, the key…

Physics and Society · Physics 2014-04-15 Wei Li , Jiao Gu , Shiping Liu , Yueying Zhu , Shengfeng Deng , Longfeng Zhao , Jihui Han , Xu Cai

Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with classical loss…

Motivated by the Bures distance, we introduce a new family of distances, \emph{relative translation invariant Wasserstein distances}, denoted by $RW_p$, as an extension of the classical Wasserstein distances $W_p$ for $p \in [1, +\infty)$.…

Machine Learning · Computer Science 2026-05-26 Binshuai Wang , Qiwei Di , Ming Yin , Mengdi Wang , Quanquan Gu , Peng Wei

A generalization of the Wasserstein metric, the integrated transportation distance, establishes a novel distance between probability kernels of Markov systems. This metric serves as the foundation for an efficient approximation technique,…

Machine Learning · Computer Science 2023-12-07 Zhengqi Lin , Andrzej Ruszczynski

This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source…

Machine Learning · Computer Science 2019-06-12 Yucheng Chen , Matus Telgarsky , Chao Zhang , Bolton Bailey , Daniel Hsu , Jian Peng