Estimation and Prediction for Stochastic Blockstructures

By Krzysztof Nowicki, Tom A. B. Snijders. 2001

1,236 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/bce1b1140472a45ca4864c1cade951ccc9893291

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Statistics and Probability

Citations in the corpus

Graph Clustering with Graph Neural Networks (2020, background): “The standard (degree-free) Stochastic Block Model (Nowicki and Snijders, 2001) is a generative graph model which divides n vertices into k classes, and then places edges between two vertices vi and vj with probability pij determined from the class assignments.”
The analysis of social networks (2008, background): “Nowicki and Snijders (2001), for example, develop a posteriori stochastic blockmodels which seek to assign actors to classes of a latent categorical variable such that actors within a class exhibit stochastically equivalent relational patterns.”
Learning Systems of Concepts with an Infinite Relational Model (2006, methodology): “Since we integrate out , inference can be carried out using Markov chain Monte Carlo methods to sample from the posterior on cluster assignments P(z|R) P(R|z)P(z) ( Jain & Neal 2004 ), or by searching for the mode of this distribution.”
Mean-field theory of graph neural networks in graph partitioning (2018, neutral): “This is called the identifiability problem [31].”
Efficient discovery of overlapping communities in massive networks (2013, methodology): “Furthermore, existing approximation methods like Markov chain Monte Carlo (30) or variational inference (24) are inefficient for real-world–sized networks because they must iteratively consider all pairs of nodes (5, 6, 10).”
Pseudo-likelihood methods for community detection in large sparse networks (2012, methodology): “In the Bayesian framework, Markov Chain Monte Carlo methods have been developed [30, 34], but they only work for networks with a few hundred nodes.”
Statistical Models for Social Networks (2011, methodology): “Examples are the neighbourhood models of Pattison and Robins (2002) and the models excluding ‘action at a distance’ discussed by Snijders (2010).”
Consistency of maximum-likelihood and variational estimators in the Stochastic Block Model (2011, methodology): “This idea has been successfully applied to social (Nowicki and Snijders, 2001) and biological (Picard et al., 2009) networks.”
Matrix estimation by Universal Singular Value Thresholding (2012, methodology): “Early analysis of the stochastic blockmodel was carried out by Snijders and Nowicki [77, 91], who provided consistent parameter estimates when there are exactly two blocks.”
Scalable Inference of Overlapping Communities (2012, methodology): “Classical methods for community detection assume that each node participates in a single community [4, 5, 6].”