Sampling perspectives on sparse exchangeable graphs

Recent work has introduced sparse exchangeable graphs and the associated graphex framework, as a generalization of dense exchangeable graphs and the associated graphon framework. The development of this subject involves the interplay between the statistical modeling of network data, the theory of large graph limits, exchangeability, and network sampling. The purpose of the present paper is to clarify the relationships between these subjects by explaining each in terms of a certain natural sampling scheme associated with the graphex model. The first main technical contribution is the introduction of sampling convergence, a new notion of graph limit that generalizes left convergence so that it becomes meaningful for the sparse graph regime. The second main technical contribution is the demonstration that the (somewhat cryptic) notion of exchangeability underpinning the graphex framework is equivalent to a more natural probabilistic invariance expressed in terms of the sampling scheme.

[1]  O. Kallenberg.  Probabilistic Symmetries and Invariance Principles , 2005 .

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

[3]  Daniel M. Roy,et al.  Sampling and Estimation for (Sparse) Exchangeable Graphs , 2016, The Annals of Statistics.

[4]  P. Diaconis,et al.  Graph limits and exchangeable random graphs , 2007, 0712.2749.

[5]  S. Janson.  On convergence for graphexes , 2017, 1702.06389.

[6]  László Lovász,et al.  Limits of dense graph sequences , 2004, J. Comb. Theory B.

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

[8]  Iosif Ilitch Gikhman,et al.  Introduction to the theory of random processes , 1969 .

[9]  V. Sós,et al.  Counting Graph Homomorphisms , 2006 .

[10]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[11]  V. Sós,et al.  Convergent Sequences of Dense Graphs II. Multiway Cuts and Statistical Physics , 2012 .

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

[13]  László Lovász,et al.  Large Networks and Graph Limits , 2012, Colloquium Publications.

[14]  Tim Austin.  On exchangeable random variables and the statistics of large graphs and hypergraphs , 2008, 0801.1698.

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

[16]  Yufei Zhao,et al.  An $L^p$ theory of sparse graph convergence I: Limits, sparse random graph models, and power law distributions , 2014, Transactions of the American Mathematical Society.

[17]  V. Sós,et al.  Convergent Sequences of Dense Graphs I: Subgraph Frequencies, Metric Properties and Testing , 2007, math/0702004.

[18]  Daryl J. Daley,et al.  An Introduction to the Theory of Point Processes , 2013 .

[19]  O. Kallenberg.  Exchangeable random measures in the plane , 1990 .

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

[21]  T. Snijders,et al.  Estimation and Prediction for Stochastic Blockstructures , 2001 .

[22]  Olav Kallenberg,et al.  Multivariate Sampling and the Estimation Problem for Exchangeable Arrays , 1999 .

[23]  Peter D. Hoff,et al.  Latent Space Approaches to Social Network Analysis , 2002 .

[24]  O. Kallenberg.  Foundations of Modern Probability , 2021, Probability Theory and Stochastic Modelling.

[25]  D. Aldous.  Representations for partially exchangeable arrays of random variables , 1981 .

[26]  Christian Borgs,et al.  An $L^{p}$ theory of sparse graph convergence II: LD convergence, quotients and right convergence , 2014, 1408.0744.

[27]  Thomas L. Griffiths,et al.  Nonparametric Latent Feature Models for Link Prediction , 2009, NIPS.

[28]  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).

[29]  B. Szegedy,et al.  Szemerédi’s Lemma for the Analyst , 2007 .

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

[31]  D. Aldous.  Probability and Mathematical Genetics: More uses of exchangeability: representations of complex random structures , 2009, 0909.4339.

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

[33]  F. Hollander.  Probability Theory : The Coupling Method , 2012 .

[34]  I. Benjamini,et al.  Recurrence of Distributional Limits of Finite Planar Graphs , 2000, math/0011019.

[35]  Svante Janson,et al.  Graphons and cut metric on sigma-finite measure spaces , 2016, 1608.01833.

[36]  Zoubin Ghahramani,et al.  Random function priors for exchangeable arrays with applications to graphs and relational data , 2012, NIPS.