Network Estimation via Graphon With Node Features

One popular model for network analysis is the exchangeable graph model (ExGM), which is characterized by a two-dimensional function known as a graphon. Estimating an underlying graphon becomes the key of such analysis. Several nonparametric estimation methods have been proposed, and some are provably consistent. However, if certain useful features of the nodes (e.g., age and schools in a social network context) are available, none of these methods were designed to incorporate this source of information to help with the estimation. This paper develops a consistent graphon estimation method that integrates information from both the adjacency matrix itself and node features. We show that properly leveraging the features can improve the estimation. A cross-validation method is proposed to automatically select the tuning parameter of the method.

• Publication year

  2018

• Venue

  IEEE Transactions on Network Science and Engineering

• Publication date

  2018-09-03

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/TNSE.2020.2973994arXiv 1809.00420
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Revealing Network Structure, Confidentially: Improved Rates for Node-Private Graphon Estimation

  2018cited by this paper
• Graphon Mean Field Games and the GMFG Equations

  2018cited by this paper
• Topics at the Frontier of Statistics and Network Analysis: (Re)Visiting the Foundations

  2017cited by this paper
• Centrality Measures for Graphons: Accounting for Uncertainty in Networks

  2017cited by this paper
• The control of arbitrary size networks of linear systems via graphon limits: An initial investigation

  2017cited by this paper
• Estimating exponential random graph models using sampled network data via graphon

  2016cited by this paper
• Network cross-validation by edge sampling

  2016cited by this paper
• Community Detection in Networks with Node Features

  2015influential reference
• Oracle inequalities for network models and sparse graphon estimation

  2015cited by this paper
• Clustering Network Layers with the Strata Multilayer Stochastic Block Model

  2015cited by this paper
• A selective overview of feature screening for ultrahigh-dimensional data

  2015cited by this paper
• Estimating network edge probabilities by neighborhood smoothing

  2015influential reference
• Reconstruction in the Labelled Stochastic Block Model

  2015cited by this paper
• Rate-optimal graphon estimation

  2014cited by this paper
• Nonparametric estimation and testing of exchangeable graph models

  2014influential reference
• Network Cross-Validation for Determining the Number of Communities in Network Data

  2014cited by this paper
• A Consistent Histogram Estimator for Exchangeable Graph Models

  2014influential reference
• Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures

  2013cited by this paper
• Ultrahigh Dimensional Feature Screening via RKHS Embeddings

  2013cited by this paper
• Lovász , Large Networks and Graph Limits

  2013cited by this paper
• Stochastic blockmodel approximation of a graphon: Theory and consistent estimation

  2013influential reference
• Nonparametric graphon estimation

  2013cited by this paper
• Estimation of exchangeable graph models by stochastic blockmodel approximation

  2013cited by this paper
• Large Networks and Graph Limits

  2012cited by this paper
• Review of statistical network analysis: models, algorithms, and software

  2012cited by this paper
• Random function priors for exchangeable arrays with applications to graphs and relational data

  2012cited by this paper
• Matrix estimation by Universal Singular Value Thresholding

  2012influential reference
• Feature Screening via Distance Correlation Learning

  2012cited by this paper
• Model-Free Feature Screening for Ultrahigh-Dimensional Data

  2011cited by this paper
• A nonparametric view of network models and Newman–Girvan and other modularities

  2009cited by this paper
• Modeling homophily and stochastic equivalence in symmetric relational data

  2007cited by this paper
• Probabilistic Symmetries and Invariance Principles

  2005cited by this paper
• Representations for partially exchangeable arrays of random variables

  1981influential reference
• Large Networks and Graph Limits

  year unknowncited by this paper

• Ordinal Embedding for Network Estimation via Graphon

  2026cites this paper
• The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

  2025cites this paper
• LOBSTUR: A Local Bootstrap Framework for Tuning Unsupervised Representations in Graph Neural Networks

  2025cites this paper
• Profile Least Squares Estimation in Networks With Covariates

  2024cites this paper
• Inference for decorated graphs and application to multiplex networks

  2024cites this paper
• AutoGFI: Streamlined Generalized Fiducial Inference for Modern Inference Problems in Models with Additive Errors

  2024cites this paper
• Estimating Dyadic Treatment Effects with Unknown Confounders

  2024cites this paper
• A Simple Latent Variable Model for Graph Learning and Inference

  2023cites this paper
• A Graph-Based Modelling of Epidemics]{A Graph-Based Modelling of Epidemics: Properties, Simulation, and Continuum Limit

  2022cites this paper
• Linear Stochastic Graphon Systems with Q-Space Noise

  2022cites this paper