Projective, sparse and learnable latent position network models

DOI10.1214/23-AOS2340zbMATH Open1530.05176arXiv1709.09702OpenAlexW2914572355MaRDI QIDQ6183873FDOQ6183873

Authors: Neil Spencer, Cosma Rohilla Shalizi 

Publication date: 4 January 2024

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: When modeling network data using a latent position model, it is typical to assume that the nodes' positions are independently and identically distributed. However, this assumption implies the average node degree grows linearly with the number of nodes, which is inappropriate when the graph is thought to be sparse. We propose an alternative assumption---that the latent positions are generated according to a Poisson point process---and show that it is compatible with various levels of sparsity. Unlike other notions of sparse latent position models in the literature, our framework also defines a projective sequence of probability models, thus ensuring consistency of statistical inference across networks of different sizes. We establish conditions for consistent estimation of the latent positions, and compare our results to existing frameworks for modeling sparse networks.

Full work available at URL: https://arxiv.org/abs/1709.09702

Recommendations

• Learning Model-Based Sparsity via Projected Gradient Descent
• Latent space models for multiview network data
• Inferring sparse Gaussian graphical models with latent structure
• A latent space model for multilayer network data
• Variational Inference for Latent Space Models for Dynamic Networks
• Sparse low-rank separated representation models for learning from data
• Latent space models for dynamic networks
• Learning and Inference in Sparse Coding Models With Langevin Dynamics
• Network-based sparse Bayesian classification

zbMATH Keywords

consistent estimationnetwork modelsrandom geometric graphprojective familylatent space modelnetwork sparsitylatent position network model

Mathematics Subject Classification ID

Applications of graph theory (05C90) Non-Markovian processes: estimation (62M09) Random graphs (graph-theoretic aspects) (05C80) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Graph theory (including graph drawing) in computer science (68R10) Small world graphs, complex networks (graph-theoretic aspects) (05C82)

Cites Work

• Random Geometric Graphs
• Matrix estimation by universal singular value thresholding
• Title not available (Why is that?)
• The Structure and Function of Complex Networks
• 1-bit matrix completion
• A useful variant of the Davis-Kahan theorem for statisticians
• Bilinear Mixed-Effects Models for Dyadic Data
• Latent Space Approaches to Social Network Analysis
• The phase transition in inhomogeneous random graphs
• Networks. An introduction.
• Graph limits and exchangeable random graphs
• Consistency under sampling of exponential random graph models
• Title not available (Why is that?)
• Random Plane Networks
• Continuum Percolation
• On a continuum percolation model
• An 𝐿^{𝑝} theory of sparse graph convergence I: Limits, sparse random graph models, and power law distributions
• Conditional marginalization for exponential random graph models
• Sparse graphs using exchangeable random measures
• Sparse exchangeable graphs and their limits via graphon processes
• A statistical framework for modern network science
• Recovering the structure of random linear graphs
• Exchangeable Random Measures for Sparse and Modular Graphs with Overlapping Communities
• On the estimation of latent distances using graph distances
• Learning random points from geometric graphs or orderings

This page was built for publication: Projective, sparse and learnable latent position network models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6183873)