• Corpus ID: 52916786

A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure

@article{Lee2019ABM,
  title={A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure},
  author={Juho Lee and Lancelot F. James and Seungjin Choi and François Caron},
  journal={ArXiv},
  year={2019},
  volume={abs/1810.01778}
}
We consider a non-projective class of inhomogeneous random graph models with interpretable parameters and a number of interesting asymptotic properties. Using the results of Bollobas et al. [2007], we show that i) the class of models is sparse and ii) depending on the choice of the parameters, the model is either scale-free, with power-law exponent greater than 2, or with an asymptotic degree distribution which is power-law with exponential cut-off. We propose an extension of the model that can… 

Figures and Tables from this paper

A Nonparametric Bayesian Model for Sparse Dynamic Multigraphs

The Dynamic Nonparametric Network Distribution (DNND) describes a generative distribution over sequences of interactions, captured as a time-evolving mixture of dynamic behavioral patterns, that is able to capture both sparse and dense behavior.

A Nonparametric Bayesian Model for Sparse Temporal Multigraphs

This work proposes a dynamic nonparametric model for interaction multigraphs that combines the sparsity of edge-exchangeableMultigraphs with dynamic clustering patterns that tend to reinforce recent behavioral patterns and yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic graph models.

Dynamic Nonparametric Edge-Clustering Model for Time-Evolving Sparse Networks

This work proposes a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns, and shows that this method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.

Scale-free Networks Well Done

A rigorous definition of power-law distributions is provided, equivalent to the definition of regularly varying distributions that are widely used in statistics and other fields, and three estimators of these exponents are identified that are proven to be statistically consistent.

References

SHOWING 1-10 OF 48 REFERENCES

Exchangeable random measures for sparse and modular graphs with overlapping communities

  • A. TodeschiniF. Caron
  • Computer Science
    Journal of the Royal Statistical Society: Series B (Statistical Methodology)
  • 2020
It is shown that the approach proposed can recover interpretable structure of real world networks and can handle graphs with thousands of nodes and tens of thousands of edges.

Bayesian inference on random simple graphs with power law degree distributions

A model for random simple graphs with a degree distribution that obeys a power law (i.e., is heavy-tailed) that is able to automatically select the appropriate power law behavior from the data by learning the parameters of the BFRY distribution via probabilistic inference.

Completely random measures for modelling block-structured sparse networks

This work re-introduce the use of block-structure for network models obeying Kallenberg’s notion of exchangeability and thereby obtain a collapsed model which both admits the inference of block and edge inhomogeneity and performs well on real network datasets.

Infinite Edge Partition Models for Overlapping Community Detection and Link Prediction

A hierarchical gamma process infinite edge partition model is proposed to factorize the binary adjacency matrix of an unweighted undirected relational network under a Bernoulli-Poisson link and it can not only discover overlapping communities and inter-community interactions, but also predict missing edges.

Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures

An introduction to Bayesian models of graphs, matrices, and other data that can be modeled by random structures is provided and results in probability theory are described that generalize de Finetti’s theorem to such data.

Sparse graphs using exchangeable random measures

  • F. CaronE. Fox
  • Computer Science
    Journal of the Royal Statistical Society. Series B, Statistical methodology
  • 2017
A scalable Hamiltonian Monte Carlo algorithm for posterior inference is presented, which is used to analyse network properties in a range of real data sets, including networks with hundreds of thousands of nodes and millions of edges.

Scale-free networks are rare

A severe test of their empirical prevalence using state-of-the-art statistical tools applied to nearly 1000 social, biological, technological, transportation, and information networks finds robust evidence that strongly scale-free structure is empirically rare, while for most networks, log-normal distributions fit the data as well or better than power laws.

Random Graphs and Complex Networks: Volume 1

This rigorous introduction to network science presents random graphs as models for real-world networks and investigates key properties, such as the connectivity of nodes, in several important models for complex networks.

Stochastic blockmodels and community structure in networks

  • B. KarrerM. Newman
  • Computer Science
    Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2011
This work demonstrates how the generalization of blockmodels to incorporate this missing element leads to an improved objective function for community detection in complex networks and proposes a heuristic algorithm forcommunity detection using this objective function or its non-degree-corrected counterpart.

Edge-exchangeable graphs and sparsity

It is shown how edge-exchangeability of graphs relates naturally to existing notions of exchangeability from clustering and other familiar combinatorial structures.