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

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 accommodate an overlapping community structure. Scalable posterior inference can be performed due to the specific choice of the link probability. We present experiments on five different real-world networks with up to 100,000 nodes and edges, showing that the model can provide a good fit to the degree distribution and recovers well the latent community structure.

[1]  Trevor Campbell,et al.  Edge-exchangeable graphs and sparsity , 2016, NIPS.

[2]  Eric D. Kolaczyk,et al.  Statistical Analysis of Network Data: Methods and Models , 2009 .

[3]  S. Resnick.  Heavy-Tail Phenomena: Probabilistic and Statistical Modeling , 2006 .

[4]  T. Mikosch.  Regular variation, subexponentiality and their applications in probability theory , 1999 .

[5]  Fan Chung Graham,et al.  The Average Distance in a Random Graph with Given Expected Degrees , 2004, Internet Math..

[6]  Jure Leskovec,et al.  Defining and evaluating network communities based on ground-truth , 2012, Knowledge and Information Systems.

[7]  F. Chung,et al.  The average distances in random graphs with given expected degrees , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[8]  H. S. Sichel,et al.  On a Distribution Representing Sentence‐Length in Written Prose , 1974 .

[9]  Edoardo M. Airoldi,et al.  Mixed Membership Stochastic Blockmodels , 2007, NIPS.

[10]  W. Dempsey,et al.  Edge Exchangeable Models for Interaction Networks , 2018, Journal of the American Statistical Association.

[11]  Morten Mørup,et al.  Completely random measures for modelling block-structured sparse networks , 2016, NIPS.

[12]  M. Betancourt.  Cruising The Simplex: Hamiltonian Monte Carlo and the Dirichlet Distribution , 2010, 1010.3436.

[13]  Emily B. Fox,et al.  Sparse graphs using exchangeable random measures , 2014, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[14]  Ilkka Norros,et al.  On a conditionally Poissonian graph process , 2006, Advances in Applied Probability.

[15]  A. Martin-Löf,et al.  Generating Simple Random Graphs with Prescribed Degree Distribution , 2006, 1509.06985.

[16]  Gordon E. Willmot,et al.  Asymptotic tail behaviour of Poisson mixtures by applications , 1990, Advances in Applied Probability.

[17]  Adrien Todeschini,et al.  Exchangeable random measures for sparse and modular graphs with overlapping communities , 2016, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[18]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[19]  Béla Bollobás,et al.  The phase transition in inhomogeneous random graphs , 2007, Random Struct. Algorithms.

[20]  David Aldous,et al.  Brownian excursions, critical random graphs and the multiplicative coalescent , 1997 .

[21]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[22]  Aaron Clauset,et al.  Scale-free networks are rare , 2018, Nature Communications.

[23]  Edoardo M. Airoldi,et al.  A Survey of Statistical Network Models , 2009, Found. Trends Mach. Learn..

[24]  W. Dempsey,et al.  A framework for statistical network modeling , 2015, 1509.08185.

[25]  Daniel M. Roy,et al.  Bayesian Models of Graphs, Arrays and Other Exchangeable Random Structures , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Zoubin Ghahramani,et al.  Bayesian inference on random simple graphs with power law degree distributions , 2017, ICML.

[27]  F. Chung,et al.  Connected Components in Random Graphs with Given Expected Degree Sequences , 2002 .

[28]  S. Janson.  On Edge Exchangeable Random Graphs , 2017, Journal of statistical physics.

[29]  Daniel M. Roy,et al.  The Class of Random Graphs Arising from Exchangeable Random Measures , 2015, ArXiv.

[30]  John Costello.  All you need is love? , 2016, International journal of palliative nursing.

[31]  Thomas Duquesne,et al.  Limits of multiplicative inhomogeneous random graphs and Lévy trees: limit theorems , 2018, Probability Theory and Related Fields.

[32]  S. Duane,et al.  Hybrid Monte Carlo , 1987 .

[33]  Remco van der Hofstad,et al.  Critical behavior in inhomogeneous random graphs , 2009, Random Struct. Algorithms.

[34]  Jure Leskovec,et al.  Overlapping community detection at scale: a nonnegative matrix factorization approach , 2013, WSDM.

[35]  Christian Borgs,et al.  Sparse Exchangeable Graphs and Their Limits via Graphon Processes , 2016, J. Mach. Learn. Res..

[36]  Mingyuan Zhou,et al.  Infinite Edge Partition Models for Overlapping Community Detection and Link Prediction , 2015, AISTATS.

[37]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[38]  Remco van der Hofstad,et al.  Novel scaling limits for critical inhomogeneous random graphs , 2009, 0909.1472.

[39]  Mark E. J. Newman,et al.  Stochastic blockmodels and community structure in networks , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[40]  Chong Wang,et al.  Modeling Overlapping Communities with Node Popularities , 2013, NIPS.

[41]  Remco van der Hofstad,et al.  Random Graphs and Complex Networks: Volume 1 , 2016 .