Community Detection with Graph Neural Networks

05/23/2017
by   Joan Bruna, et al.
0

We study data-driven methods for community detection in graphs. This estimation problem is typically formulated in terms of the spectrum of certain operators, as well as via posterior inference under certain probabilistic graphical models. Focusing on random graph families such as the Stochastic Block Model, recent research has unified these two approaches, and identified both statistical and computational signal-to-noise detection thresholds. We embed the resulting class of algorithms within a generic family of graph neural networks and show that they can reach those detection thresholds in a purely data-driven manner, without access to the underlying generative models and with no parameter assumptions. The resulting model is also tested on real datasets, requiring less computational steps and performing significantly better than rigid parametric models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2022

Graph Neural Networks for Community Detection on Sparse Graphs

Spectral methods provide consistent estimators for community detection i...
research
01/08/2022

VGAER: graph neural network reconstruction based community detection

Community detection is a fundamental and important issue in network scie...
research
05/17/2020

Deep Learning for Community Detection: Progress, Challenges and Opportunities

As communities represent similar opinions, similar functions, similar pu...
research
03/03/2021

Recurrent Graph Neural Network Algorithm for Unsupervised Network Community Detection

Network community detection often relies on optimizing partition quality...
research
09/30/2017

Bayesian estimation from few samples: community detection and related problems

We propose an efficient meta-algorithm for Bayesian estimation problems ...
research
01/21/2019

Exact Recovery for a Family of Community-Detection Generative Models

Generative models for networks with communities have been studied extens...
research
02/13/2018

Community detection through likelihood optimization: in search of a sound model

Community detection has recently became one of the most important proble...

Please sign up or login with your details

Forgot password? Click here to reset