Phase Transitions in Community Detection: A Solvable Toy Model

12/02/2013
by   Greg Ver Steeg, et al.
0

Recently, it was shown that there is a phase transition in the community detection problem. This transition was first computed using the cavity method, and has been proved rigorously in the case of q=2 groups. However, analytic calculations using the cavity method are challenging since they require us to understand probability distributions of messages. We study analogous transitions in so-called "zero-temperature inference" model, where this distribution is supported only on the most-likely messages. Furthermore, whenever several messages are equally likely, we break the tie by choosing among them with equal probability. While the resulting analysis does not give the correct values of the thresholds, it does reproduce some of the qualitative features of the system. It predicts a first-order detectability transition whenever q > 2, while the finite-temperature cavity method shows that this is the case only when q > 4. It also has a regime analogous to the "hard but detectable" phase, where the community structure can be partially recovered, but only when the initial messages are sufficiently accurate. Finally, we study a semisupervised setting where we are given the correct labels for a fraction ρ of the nodes. For q > 2, we find a regime where the accuracy jumps discontinuously at a critical value of ρ.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/30/2014

Phase transitions in semisupervised clustering of sparse networks

Predicting labels of nodes in a network, such as community memberships o...
research
04/09/2015

Phase Transitions in Spectral Community Detection of Large Noisy Networks

In this paper, we study the sensitivity of the spectral clustering based...
research
05/22/2018

Community Detection with Side Information: Exact Recovery under the Stochastic Block Model

The community detection problem involves making inferences about node la...
research
04/07/2021

Community Detection with Contextual Multilayer Networks

In this paper, we study community detection when we observe m sparse net...
research
10/26/2022

Grokking phase transitions in learning local rules with gradient descent

We discuss two solvable grokking (generalisation beyond overfitting) mod...
research
08/14/2023

Nonequilibrium phase transition of a one dimensional system reaches the absorbing state by two different ways

We study the nonequilibrium phase transitions from the absorbing phase t...
research
02/14/2015

Gray-Level Image Transitions Driven by Tsallis Entropic Index

The maximum entropy principle is largely used in thresholding and segmen...

Please sign up or login with your details

Forgot password? Click here to reset