English
Related papers

Related papers: Learning Graphons via Structured Gromov-Wasserstei…

200 papers

Graphs are ubiquitous in various fields, and deep learning methods have been successful applied in graph classification tasks. However, building large and diverse graph datasets for training can be expensive. While augmentation techniques…

Machine Learning · Computer Science 2024-04-15 Andrea Ponti

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called \textit{graphon autoencoder} to build an interpretable…

Machine Learning · Computer Science 2021-06-01 Hongteng Xu , Peilin Zhao , Junzhou Huang , Dixin Luo

We propose a new nonlinear factorization model for graphs that are with topological structures, and optionally, node attributes. This model is based on a pseudometric called Gromov-Wasserstein (GW) discrepancy, which compares graphs in a…

Machine Learning · Computer Science 2019-11-21 Hongteng Xu

Pairwise comparison of graphs is key to many applications in Machine learning ranging from clustering, kernel-based classification/regression and more recently supervised graph prediction. Distances between graphs usually rely on…

Machine Learning · Statistics 2023-09-29 Junjie Yang , Matthieu Labeau , Florence d'Alché-Buc

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

Graphons are general and powerful models for generating graphs of varying size. In this paper, we propose to directly model graphons using neural networks, obtaining Implicit Graphon Neural Representation (IGNR). Existing work in modeling…

Machine Learning · Computer Science 2023-04-03 Xinyue Xia , Gal Mishne , Yusu Wang

Graphons, as limit objects of dense graph sequences, play a central role in the statistical analysis of network data. However, existing graphon estimation methods often struggle with scalability to large networks and resolution-independent…

Machine Learning · Computer Science 2025-06-05 Reza Ramezanpour , Victor M. Tenorio , Antonio G. Marques , Ashutosh Sabharwal , Santiago Segarra

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

Graph neural networks (GNNs) use graph convolutions to exploit network invariances and learn meaningful feature representations from network data. However, on large-scale graphs convolutions incur in high computational cost, leading to…

Machine Learning · Computer Science 2022-06-29 Juan Cervino , Luana Ruiz , Alejandro Ribeiro

We study graphons as a non-parametric generalization of stochastic block models, and show how to obtain compactly represented estimators for sparse networks in this framework. Our algorithms and analysis go beyond previous work in several…

Statistics Theory · Mathematics 2016-02-25 Christian Borgs , Jennifer T. Chayes , Henry Cohn , Shirshendu Ganguly

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discrepancy, we measure the dissimilarity between two graphs and…

Machine Learning · Computer Science 2019-05-08 Hongteng Xu , Dixin Luo , Hongyuan Zha , Lawrence Carin

This paper introduces a novel and generic framework to solve the flagship task of supervised labeled graph prediction by leveraging Optimal Transport tools. We formulate the problem as regression with the Fused Gromov-Wasserstein (FGW) loss…

Machine Learning · Statistics 2022-06-27 Luc Brogat-Motte , Rémi Flamary , Céline Brouard , Juho Rousu , Florence d'Alché-Buc

Non-parametric approaches for analyzing network data based on exchangeable graph models (ExGM) have recently gained interest. The key object that defines an ExGM is often referred to as a graphon. This non-parametric perspective on network…

Methodology · Statistics 2013-11-14 Edoardo M Airoldi , Thiago B Costa , Stanley H Chan

In a recent paper, Caron and Fox suggest a probabilistic model for sparse graphs which are exchangeable when associating each vertex with a time parameter in $\mathbb{R}_+$. Here we show that by generalizing the classical definition of…

Probability · Mathematics 2018-06-21 Christian Borgs , Jennifer T. Chayes , Henry Cohn , Nina Holden

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

Graph neural networks (GNNs) are learning architectures that rely on knowledge of the graph structure to generate meaningful representations of large-scale network data. GNN stability is thus important as in real-world scenarios there are…

Machine Learning · Computer Science 2021-04-27 Luana Ruiz , Zhiyang Wang , Alejandro Ribeiro

In this work, we propose to train a graph neural network via resampling from a graphon estimate obtained from the underlying network data. More specifically, the graphon or the link probability matrix of the underlying network is first…

Machine Learning · Computer Science 2021-09-07 Ziqing Hu , Yihao Fang , Lizhen Lin

Graphons are limit objects of sequences of graphs and are used to analyze the behavior of large graphs. Recently, graphon signal processing has been developed to study signal processing on large graphs. A major limitation of this approach…

Signal Processing · Electrical Eng. & Systems 2024-03-26 Feng Ji , Xingchao Jian , Wee Peng Tay

Graphons are continuous models that represent the structure of graphs and allow the generation of graphs of varying sizes. We propose Scalable Implicit Graphon Learning (SIGL), a scalable method that combines implicit neural representations…

Machine Learning · Statistics 2025-05-23 Ali Azizpour , Nicolas Zilberstein , Santiago Segarra

Recovering the random graph model from an observed collection of networks is known to present significant challenges in the setting, where the networks do not share a common node set and have different sizes. More specifically, the goal is…

Methodology · Statistics 2026-03-17 Roland Boniface Sogan , Tabea Rebafka
‹ Prev 1 2 3 10 Next ›